{"ok":true,"count":12,"total":12,"page":1,"pages":1,"per_page":24,"limit":24,"sort":"relevance","next_page":null,"gateway":"/mcphub/mcp","note":"Каталог MCP-серверов. Для вызова инструментов агентам — MCP-эндпоинт /mcphub/mcp.","servers":[{"slug":"pdfmathtranslate","name":"Перевод PDF с сохранением формул","original_name":"PDFMathTranslate","description":"Инструмент для перевода научных статей и документов, сохраняющий структуру, таблицы и математические формулы. Работает как CLI-утилита и MCP-сервер.","original_description":"Инструмент для перевода научных статей и документов, сохраняющий структуру, таблицы и математические формулы. Работает как CLI-утилита и MCP-сервер.","repository":"https://github.com/PDFMathTranslate/PDFMathTranslate","transport":"stdio","auth":"none","categories":["data"],"health_status":"unverified","health_checked_at":"2026-10-24 07:33:22.659313+03","stars":37806,"latency_ms":null,"readiness":"needs_install","tools":[],"install":"","remote":"","trust":80,"calls":0,"success_rate":null,"feedback_count":0,"agent_rating":null,"agent_reviews_count":0,"utility_score":0,"safety_score":0,"audit_verdict":"","is_gem":false,"audit_summary":"","page_url":"/mcphub/pdfmathtranslate"},{"slug":"xberg","name":"Xberg Document Intelligence","original_name":"xberg","description":"Движок для извлечения текста, таблиц и структурированных данных из документов любого формата. Поддерживает OCR, транскрибацию аудио и анализ кода.","original_description":"Движок для извлечения текста, таблиц и структурированных данных из документов любого формата. Поддерживает OCR, транскрибацию аудио и анализ кода.","repository":"https://github.com/xberg-io/xberg","transport":"unknown","auth":"none","categories":["data"],"health_status":"unverified","health_checked_at":"2026-10-24 07:33:29.45156+03","stars":9442,"latency_ms":null,"readiness":"needs_install","tools":[],"install":"","remote":"","trust":80,"calls":0,"success_rate":null,"feedback_count":0,"agent_rating":null,"agent_reviews_count":0,"utility_score":0,"safety_score":0,"audit_verdict":"","is_gem":false,"audit_summary":"","page_url":"/mcphub/xberg"},{"slug":"agency-justidea-justidea-agency","name":"JustIdea Agency","original_name":"JustIdea Agency","description":"Услуги, цены, запросы и бесплатный анализ от JustIdea (Польша), сканирование видимости в AI и Google.","original_description":"Services, prices, inquiries and free analytics, AI and Google visibility scans by JustIdea, Poland.","repository":"","transport":"streamable_http","auth":"none","categories":["development","data","ai"],"health_status":"operational","health_checked_at":"2026-10-24 12:58:12.228173+03","stars":0,"latency_ms":"2049","readiness":"stale","tools":[{"name":"list_services","description":"List JustIdea Agency services with the published starting (\"from\") prices and links. Returns the price list (12 service categories, each with its packages) and every service page with its short description. All prices are net (VAT excluded) and exactly as published on justidea.agency. Use get page for the full scope of a service and search site for city pages, case studies and articles.","inputSchema":{"type":"object","properties":{"language":{"enum":["pl","en"],"type":"string","default":"pl","description":"Site language: \"pl\" (prices in PLN) or \"en\" (prices in EUR for clients outside Poland)."}},"additionalProperties":false}},{"name":"get_page","description":"Full text of one justidea.agency page as Markdown: a service, a price list, the company profile, reviews, a blog article. Accepts a full URL or a path, e.g. \"/pl/cennik/sklepy-internetowe/\" or \"https://justidea.agency/en/pricing/online-stores/\". Only pages published on the site; use list services or search site to find the URL.","inputSchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","maxLength":500,"minLength":1,"description":"Page URL or path on justidea.agency."}},"additionalProperties":false}},{"name":"search_site","description":"Search justidea.agency pages by titles, descriptions and section headings. Polish and English queries both work. Returns titles, URLs and descriptions; read a result with get page.","inputSchema":{"type":"object","required":["query"],"properties":{"kind":{"enum":["services_index","service_area","service","city_page","pricing","case_studies","event","blog","company"],"type":"string","description":"Limit to one kind of page."},"limit":{"type":"integer","default":8,"maximum":25,"minimum":1},"query":{"type":"string","maxLength":200,"minLength":2,"description":"What to look for, e.g. \"PrestaShop migration\", \"sklep internetowy Kraków\", \"SEO price\"."},"language":{"enum":["pl","en","any"],"type":"string","default":"any","description":"Limit to one site language."}},"additionalProperties":false}},{"name":"send_inquiry","description":"Send a sales inquiry to JustIdea Agency (Kraków, Poland) on behalf of the user. It goes to the agency CRM and the sales team, the sender gets a short confirmation e-mail, and a person replies within one business day. Use only details the user gave you. Never invent a name, e-mail or phone number. Before sending, show the user what will be sent and ask for consent to data processing under the privacy policy (https://justidea.agency/en/privacy-policy/); set zgoda to true only after they agree. Budgets are in PLN net (\"tys. zł\" = thousand PLN). At most 2 inquiries per e-mail address per day. Urge","inputSchema":{"type":"object","required":["imie","email","telefon","usluga","budzet","wiadomosc","zgoda"],"properties":{"imie":{"type":"string","maxLength":120,"minLength":2,"description":"Full name of the person sending the inquiry."},"email":{"type":"string","format":"email","maxLength":200,"description":"Email address for the reply."},"firma":{"type":"string","maxLength":200,"description":"Company name, optional."},"zgoda":{"type":"boolean","const":true,"description":"Must be true: the user agreed to the processing of the data in this inquiry under the privacy policy."},"budzet":{"enum":["do 15 tys. zł","15-40 tys. zł","40-80 tys. zł","80-150 tys. zł","150-300 tys. zł","powyżej 300 tys. zł","jeszcze nie wiem","do 2 tys. zł","2-6 tys. zł","6-15 tys. zł","40-100 tys. zł","powyżej 100 tys. zł"],"type":"string","description":"Budget range, exactly one of the listed values, and it must match the service. One-off projects (\"sklep\", \"strona\", \"audyt\", \"kreacja\", \"inne\") take a project budget: \"do 15 tys. zł\", \"15-40 tys. zł\", \"40-80 tys. zł\", \"80-150 tys. zł\", \"150-300 tys. zł\", \"powyżej 300 tys. zł\", \"jeszcze nie wiem\". Monthly services (\"seo\", \"wizytowka\", \"kampanie\", \"marketing\", \"content\", \"opieka\") take a monthly budget: \"do 2 tys. zł\", \"2-6 tys. zł\", \"6-15 tys. zł\", \"15-40 tys. zł\", \"40-100 tys. zł\", \"powyżej 100 tys. zł\", \"jeszcze nie wiem\". If the user does not know the budget, use \"jeszcze nie wiem\" instead of guessing."},"strona":{"type":"string","maxLength":300,"description":"Current website or online store address, optional."},"usluga":{"enum":["sklep","strona","seo","wizytowka","kampanie","marketing","content","opieka","audyt","kreacja","inne"],"type":"string","description":"What the inquiry is about: \"sklep\" = Sklep internetowy; \"strona\" = Strona internetowa; \"seo\" = Pozycjonowanie SEO; \"wizytowka\" = Wizytówka Google i Bing; \"kampanie\" = Kampanie reklamowe; \"marketing\" = Marketing, pełny zakres; \"content\" = Content marketing i treści; \"opieka\" = Opieka i rozwój serwisu; \"audyt\" = Audyt; \"kreacja\" = Identyfikacja i kreacja; \"inne\" = Coś innego."},"telefon":{"type":"string","maxLength":60,"minLength":9,"description":"Phone number with at least 9 digits, country code welcome."},"wiadomosc":{"type":"string","maxLength":5000,"minLength":20,"description":"The request in the user's own language, at least two sentences: what they need, scope, deadline."}}}},{"name":"scan_analytics","description":"Free check of how a website or online store measures traffic and sales: Google Tag Manager, GA4 and e-commerce events, consent banner and Consent Mode v2, server-side tagging, Meta Pixel and Conversions API. A real browser visits the site (home, product page, cart) for up to 90 seconds. Returns the grade (A-F), the score and the list of problems, without fixes. The full report with step-by-step fixes and a PDF is sent by JustIdea Agency to the user's e-mail. Use only details the user gave you: never invent or guess an e-mail address. Before calling, tell the user the report goes to their e-mai","inputSchema":{"type":"object","required":["url","email","zgoda"],"properties":{"url":{"type":"string","maxLength":300,"minLength":3,"description":"The website to scan: a domain or URL, e.g. \"mystore.com\". Only the home domain is used."},"name":{"type":"string","maxLength":80,"description":"Optional. The user's first name, only if they gave it."},"email":{"type":"string","format":"email","maxLength":254,"description":"The user's own e-mail address. The full report with fixes is sent there, and only there."},"phone":{"type":"string","maxLength":40,"description":"Optional. The user's phone number, only if they gave it and want a call about the results."},"zgoda":{"type":"boolean","const":true,"description":"Must be true: the user agreed to receive the report by e-mail, to be contacted by JustIdea about the results, and to the processing of this data under the privacy policy."},"language":{"enum":["pl","en"],"type":"string","default":"pl","description":"Report language. Use \"pl\" for Polish-speaking users, \"en\" for everyone else."}},"additionalProperties":false}},{"name":"scan_ai_visibility","description":"Free check of how ready a website is for AI assistants and AI search (ChatGPT, Perplexity, Gemini, Claude): whether their crawlers get in (robots.txt, firewalls), whether the content is readable without JavaScript, structured data, llms.txt and the signals models use to cite a source. Takes about 10-30 seconds. Returns the grade (A-F), the score and the list of problems, without fixes. The full report with step-by-step fixes and a PDF is sent by JustIdea Agency to the user's e-mail. Use only details the user gave you: never invent or guess an e-mail address. Before calling, tell the user the r","inputSchema":{"type":"object","required":["url","email","zgoda"],"properties":{"url":{"type":"string","maxLength":300,"minLength":3,"description":"The website to scan: a domain or URL, e.g. \"mystore.com\". Only the home domain is used."},"name":{"type":"string","maxLength":80,"description":"Optional. The user's first name, only if they gave it."},"email":{"type":"string","format":"email","maxLength":254,"description":"The user's own e-mail address. The full report with fixes is sent there, and only there."},"phone":{"type":"string","maxLength":40,"description":"Optional. The user's phone number, only if they gave it and want a call about the results."},"zgoda":{"type":"boolean","const":true,"description":"Must be true: the user agreed to receive the report by e-mail, to be contacted by JustIdea about the results, and to the processing of this data under the privacy policy."},"language":{"enum":["pl","en"],"type":"string","default":"pl","description":"Report language. Use \"pl\" for Polish-speaking users, \"en\" for everyone else."}},"additionalProperties":false}},{"name":"scan_google_visibility","description":"Free check of whether Google can index a website well: Googlebot access in robots.txt and on the server, noindex, canonical, http-to-https and www redirects, the sitemap and whether its URLs answer 200, titles, meta descriptions, H1, structured data, mobile viewport, hreflang and Core Web Vitals from real Chrome users. Takes about 15-60 seconds. Returns the grade (A-F), the score and the list of problems, without fixes. When available, it also returns an Ahrefs estimate of the domain in Google (ranking keywords, monthly organic traffic, Domain Rating, referring domains). These numbers are esti","inputSchema":{"type":"object","required":["url","email","zgoda"],"properties":{"url":{"type":"string","maxLength":300,"minLength":3,"description":"The website to scan: a domain or URL, e.g. \"mystore.com\". Only the home domain is used."},"name":{"type":"string","maxLength":80,"description":"Optional. The user's first name, only if they gave it."},"email":{"type":"string","format":"email","maxLength":254,"description":"The user's own e-mail address. The full report with fixes is sent there, and only there."},"phone":{"type":"string","maxLength":40,"description":"Optional. The user's phone number, only if they gave it and want a call about the results."},"zgoda":{"type":"boolean","const":true,"description":"Must be true: the user agreed to receive the report by e-mail, to be contacted by JustIdea about the results, and to the processing of this data under the privacy policy."},"language":{"enum":["pl","en"],"type":"string","default":"pl","description":"Report language. Use \"pl\" for Polish-speaking users, \"en\" for everyone else."}},"additionalProperties":false}},{"name":"get_scan_result","description":"Result of a scan started with scan analytics, scan ai visibility or scan google visibility that was still running. Returns the same grade and problem list; sends the full report by e-mail if it has not gone yet. Scan IDs expire after 2 days.","inputSchema":{"type":"object","required":["scan_id"],"properties":{"scan_id":{"type":"string","pattern":"^[a-z0-9]{16}$","description":"The scan_id returned by the scan tool."}},"additionalProperties":false}}],"install":"","remote":"https://justidea.agency/mcp","trust":58,"calls":0,"success_rate":null,"feedback_count":0,"agent_rating":null,"agent_reviews_count":0,"utility_score":85,"safety_score":93,"audit_verdict":"gem","is_gem":true,"audit_summary":"Сервер JustIdea Agency представляет собой надежный источник структурированных данных о цифровых услугах и автоматизированный инструмент аудита видимости сайтов в поисковых системах и AI. Живой тест подтвердил способность сервера возвращать актуальные прайс-листы без авторизации, что позволяет агентам формировать точные коммерческие предложения и проводить техническую диагностику веб-ресурсов на основе реальных данных, а не галлюцинаций модели.","page_url":"/mcphub/agency-justidea-justidea-agency"},{"slug":"app-elasticflow-mcp","name":"Elasticflow","original_name":"Elasticflow","description":"Рабочее пространство для команд с таблицами, документами, автоматизацией рабочих процессов и аналитикой.","original_description":"AI-native team workspace — tables, documents, workflow automation, live dashboards & analytics","repository":"https://github.com/elasticflowapp/elasticflow-mcp","transport":"streamable_http","auth":"none","categories":["data","ai","files"],"health_status":"degraded","health_checked_at":"2026-10-24 19:39:33.557605+03","stars":0,"latency_ms":"1610","readiness":"stale","tools":[],"install":"","remote":"https://mcp.elasticflow.app/mcp","trust":15,"calls":0,"success_rate":null,"feedback_count":0,"agent_rating":null,"agent_reviews_count":0,"utility_score":0,"safety_score":0,"audit_verdict":"","is_gem":false,"audit_summary":"","page_url":"/mcphub/app-elasticflow-mcp"},{"slug":"app-faqai-mcp-server","name":"FAQai","original_name":"FAQai","description":"Превращает любой документ в готовый набор данных для RAG из Claude, Cursor или любого хоста MCP.","original_description":"Turn any document into a production-ready RAG dataset from Claude, Cursor, or any MCP host.","repository":"https://github.com/Lemuran/faqai-app","transport":"stdio","auth":"api_key","categories":["data","ai","files"],"health_status":"unverified","health_checked_at":null,"stars":0,"latency_ms":null,"readiness":"needs_install","tools":[],"install":"npx -y @faqai/mcp-server@0.5.1","remote":"","trust":30,"calls":0,"success_rate":null,"feedback_count":0,"agent_rating":null,"agent_reviews_count":0,"utility_score":0,"safety_score":0,"audit_verdict":"","is_gem":false,"audit_summary":"","page_url":"/mcphub/app-faqai-mcp-server"},{"slug":"git-mcp","name":"GitMCP","original_name":"GitMCP","description":"Превращает репозитории GitHub в источник документации для AI-ассистентов. Нужен разработчикам для точной работы с актуальным кодом и API.","original_description":"Превращает репозитории GitHub в источник документации для AI-ассистентов, устраняя галлюцинации кода. Нужен разработчикам для точной работы с актуальным кодом и API.","repository":"https://github.com/idosal/git-mcp","transport":"stdio","auth":"none","categories":["development","data","ai"],"health_status":"unverified","health_checked_at":"2026-10-23 16:42:47.135015+03","stars":8477,"latency_ms":null,"readiness":"needs_install","tools":[],"install":"npx -y mcp-remote@0.15.2","remote":"","trust":80,"calls":0,"success_rate":null,"feedback_count":0,"agent_rating":null,"agent_reviews_count":0,"utility_score":0,"safety_score":0,"audit_verdict":"","is_gem":false,"audit_summary":"","page_url":"/mcphub/git-mcp"},{"slug":"ai-judt-mcp","name":"Judt","original_name":"Judt","description":"Apps and sites for your agent, with databases, storage, queues and workflows built in.","original_description":"Apps and sites for your agent, with databases, storage, queues and workflows built in.","repository":"","transport":"streamable_http","auth":"none","categories":["data","ai","files"],"health_status":"unverified","health_checked_at":null,"stars":0,"latency_ms":null,"readiness":"stale","tools":[],"install":"","remote":"https://api.judt.ai/mcp","trust":50,"calls":0,"success_rate":null,"feedback_count":0,"agent_rating":null,"agent_reviews_count":0,"utility_score":0,"safety_score":0,"audit_verdict":"","is_gem":false,"audit_summary":"","page_url":"/mcphub/ai-judt-mcp"},{"slug":"ai-getvda-minio-and-redis-storage-stack","name":"MinIO and Redis Storage Stack","original_name":"minio-and-redis-storage-stack","description":"Стек хранилищ MinIO и Redis.","original_description":"MinIO and Redis Storage Stack","repository":"","transport":"streamable_http","auth":"none","categories":["data","ai","files"],"health_status":"operational","health_checked_at":"2026-10-24 19:40:19.420148+03","stars":0,"latency_ms":"3347","readiness":"stale","tools":[{"name":"invoke","description":"Generate a production-ready docker-compose.yml for a multi-service infrastructure stack — messaging (Kafka/ZooKeeper, RabbitMQ, NATS), object storage (MinIO), search (Elasticsearch/OpenSearch), databases, caches, web servers and auth (Keycloak/Vault). Every service is health-checked, on a private bridge network, with named volumes and a matching .env.example. Kafka auto-wires its required ZooKeeper.","inputSchema":{"type":"object","required":["input"],"properties":{"input":{"type":"string","description":"JSON request for this capability (the same body you'd send as an A2A message)."}}}},{"name":"selftest","description":"FREE, no payment required. Runs this agent's real capability on a fixed canned input and returns the genuine result, an honest assertion grade, and the full trust manifest (signed Agent Card, JWKS, governance/licence chain, safety posture) with a proof link for every claim. Intended for registries, graders and auditors: this is behavioural evidence, not a self-description.","inputSchema":{"type":"object","properties":{}}}],"install":"","remote":"https://redis-minio-stack-generator-minio-minio.getvda.ai/mcp","trust":45,"calls":0,"success_rate":null,"feedback_count":0,"agent_rating":null,"agent_reviews_count":0,"utility_score":0,"safety_score":0,"audit_verdict":"","is_gem":false,"audit_summary":"","page_url":"/mcphub/ai-getvda-minio-and-redis-storage-stack"},{"slug":"ai-smithery-mistersandfr-supabase-mcp-selfhosted","name":"MisterSandFR-supabase-mcp-selfhosted","original_name":"MisterSandFR-supabase-mcp-selfhosted","description":"Управляет проектами Supabase целиком: база данных, аутентификация, хранилище, реальное время и миграции.","original_description":"Manage Supabase projects end to end across database, auth, storage, realtime, and migrations. Moni…","repository":"https://github.com/MisterSandFR/Supabase-MCP-SelfHosted","transport":"streamable_http","auth":"api_key","categories":["data","ai","files"],"health_status":"degraded","health_checked_at":"2026-10-24 19:16:05.861475+03","stars":0,"latency_ms":"2903","readiness":"needs_key","tools":[],"install":"","remote":"https://server.smithery.ai/@MisterSandFR/supabase-mcp-selfhosted/mcp","trust":15,"calls":0,"success_rate":null,"feedback_count":0,"agent_rating":null,"agent_reviews_count":0,"utility_score":0,"safety_score":0,"audit_verdict":"","is_gem":false,"audit_summary":"","page_url":"/mcphub/ai-smithery-mistersandfr-supabase-mcp-selfhosted"},{"slug":"ai-svtr-aidb","name":"SVTR AI Venture Database","original_name":"SVTR AI Venture Database","description":"Содержит верифицированные данные о финансировании ИИ-стартапов, профилях организаций и основателей. Предоставляет статистику по рынкам США и Китая, а также информацию о секторах и инвестициях.","original_description":"Curated & traceable AI venture data: verified funding events, org & founder profiles, US + China","repository":"","transport":"streamable_http","auth":"none","categories":["data","ai","files"],"health_status":"operational","health_checked_at":"2026-10-24 19:16:22.606691+03","stars":0,"latency_ms":"8769","readiness":"stale","tools":[{"name":"search_organizations","description":"搜索 SVTR AI 创投库的公司与投资机构（按名称/别名，如 \"Anthropic\"、\"a16z\"）。Search AI companies and investors in the SVTR AI Venture Database by name or alias.","inputSchema":{"type":"object","required":["query"],"properties":{"lang":{"enum":["zh","en"],"type":"string","description":"Output language, default zh (Chinese)."},"type":{"enum":["company","investor"],"type":"string","description":"Restrict to AI companies or investors; omit for both."},"limit":{"type":"integer","maximum":10,"minimum":1,"description":"Max results (default 5)."},"query":{"type":"string","description":"Company or investor name/alias, 2-80 chars."}}}},{"name":"get_organization_profile","description":"按名称或 slug 取一家公司/投资机构的公开档案：简介、赛道、总部、累计融资、近期融资史（含来源链接）、投资机构的代表出手。Get the public profile of one organization: intro, sector, HQ, total funding, recent funding rounds with sources.","inputSchema":{"type":"object","required":["ref"],"properties":{"ref":{"type":"string","description":"Organization name, alias, or svtr.ai slug."},"lang":{"enum":["zh","en"],"type":"string","description":"Output language, default zh (Chinese)."}}}},{"name":"get_person_profile","description":"按姓名或 slug 取一位创始人/投资人的公开档案：现任机构与职务、工作经历、教育背景。Get the public profile of one founder or investor: current roles, work experience, education.","inputSchema":{"type":"object","required":["ref"],"properties":{"ref":{"type":"string","description":"Person name or svtr.ai slug."},"lang":{"enum":["zh","en"],"type":"string","description":"Output language, default zh (Chinese)."}}}},{"name":"get_recent_funding_events","description":"最近 7 天的已核实 AI 融资事件（公开档位时间窗），可按赛道/阶段/公司名等单一维度筛选。Verified AI funding events from the last 7 days (public-tier window), filterable by one dimension.","inputSchema":{"type":"object","properties":{"lang":{"enum":["zh","en"],"type":"string","description":"Output language, default zh (Chinese)."},"year":{"type":"integer","maximum":2030,"minimum":2020,"description":"Filter by announced year."},"stage":{"enum":["天使轮","Pre-Seed","种子轮","A轮","B轮","C轮","D轮及以后","Pre-IPO轮","IPO","战略投资","债务/可转债","政府/科研资助","二级/老股转让","代币融资","股权+债务","未披露"],"type":"string","description":"Normalized funding stage."},"sector":{"enum":["算力","数据","训练与推理栈","互连","大模型","垂类模型","开发平台","智能体","优化测评","生命科学","企业服务","金融服务","安全合规","机器人","零售营销","开发者","效率工具","社交文娱","双碳环保","垂类行业","法律服务","教育培训","交通物流","国防安防","地产科技","工业制造","智能硬件"],"type":"string","description":"SVTR standard sector (26 values)."},"company":{"type":"string","description":"Company name filter."},"country":{"type":"string","description":"HQ country (Chinese name, e.g. 美国/中国)."}}}},{"name":"get_sector_landscape","description":"AI 赛道融资景观聚合统计：总额/笔数/中位数，全库赛道 Top10 或单赛道的阶段分布。仅聚合数字，无行级数据。Aggregated funding landscape: totals, top sectors, or stage breakdown for one sector.","inputSchema":{"type":"object","properties":{"lang":{"enum":["zh","en"],"type":"string","description":"Output language, default zh (Chinese)."},"year":{"type":"integer","maximum":2030,"minimum":2020,"description":"Filter by announced year."},"sector":{"enum":["算力","数据","训练与推理栈","互连","大模型","垂类模型","开发平台","智能体","优化测评","生命科学","企业服务","金融服务","安全合规","机器人","零售营销","开发者","效率工具","社交文娱","双碳环保","垂类行业","法律服务","教育培训","交通物流","国防安防","地产科技","工业制造","智能硬件"],"type":"string","description":"Omit for cross-sector Top 10 landscape."}}}},{"name":"get_active_investors","description":"哪些投资机构在投某个方向：按近 24 个月已确认出手笔数排名的活跃投资机构（如「投资 AI4S 的机构有哪些」）。sector 用 SVTR 标准赛道，tag 用行业主题标签（AI4S / 智能体 / 人形机器人 / 药物发现 等，见 svtr.ai/orgs）。标签与赛道说的都是 被投公司 的属性，不是机构自己的。Which investors back a given sector or topic: active AI investors ranked by confirmed deals in the last 24 months.","inputSchema":{"type":"object","properties":{"tag":{"type":"string","description":"SVTR industry topic tag of the portfolio companies (e.g. AI4S, 智能体, 人形机器人). Mutually exclusive with sector; if both are given, sector wins and the tag is reported as ignored."},"lang":{"enum":["zh","en"],"type":"string","description":"Output language, default zh (Chinese)."},"sector":{"enum":["算力","数据","训练与推理栈","互连","大模型","垂类模型","开发平台","智能体","优化测评","生命科学","企业服务","金融服务","安全合规","机器人","零售营销","开发者","效率工具","社交文娱","双碳环保","垂类行业","法律服务","教育培训","交通物流","国防安防","地产科技","工业制造","智能硬件"],"type":"string","description":"SVTR standard sector of the portfolio companies. Mutually exclusive with tag."}}}},{"name":"get_comparable_companies","description":"某家 AI 公司的可比公司：按美国 / 中国 / 欧洲分组，每组至多 3 家，列最近轮次与时间、累计融资、已披露估值，以及可核对的对标理由（同细分赛道 / 同赛道 / 同阶段 / 累计融资同一量级）。与 svtr.ai 公司详情页「可比公司」同一份数据。Comparable companies for one AI company, grouped by US / China / Europe (up to 3 each), with latest round, total raised, disclosed valuation and verifiable match reasons.","inputSchema":{"type":"object","required":["ref"],"properties":{"ref":{"type":"string","description":"Company slug, UUID, or name / alias (e.g. \"lovable\", \"逐际动力\")."},"lang":{"enum":["zh","en"],"type":"string","description":"Output language, default zh (Chinese)."}}}},{"name":"search_svtr_articles","description":"搜索 SVTR 原创研究文章（Thesis 投资论文 / Profile 创始人深度 / Radar 事件判断 / 周报等，已发布口径）。Search SVTR original research articles.","inputSchema":{"type":"object","required":["query"],"properties":{"lang":{"enum":["zh","en"],"type":"string","description":"Output language, default zh (Chinese)."},"limit":{"type":"integer","maximum":10,"minimum":1,"description":"Max results (default 5)."},"query":{"type":"string","description":"Keyword in title or summary, 2-80 chars."}}}},{"name":"get_svtr_stats","description":"SVTR AI 创投库对外统计：已收录 AI 公司数、投资机构数、人物数、已核实融资轮数、原创文章数。Public counts of the SVTR AI Venture Database.","inputSchema":{"type":"object","properties":{}}}],"install":"","remote":"https://svtr.ai/api/mcp","trust":45,"calls":0,"success_rate":null,"feedback_count":0,"agent_rating":null,"agent_reviews_count":0,"utility_score":0,"safety_score":0,"audit_verdict":"","is_gem":false,"audit_summary":"","page_url":"/mcphub/ai-svtr-aidb"},{"slug":"ai-tenderhunt-agent","name":"TenderHunt","original_name":"TenderHunt","description":"Госзакупки Беларуси: поиск, аналитика, документы и уведомления через агента TenderHunt.","original_description":"Belarus public tenders: search, analytics, docs, and alerts via TenderHunt agent.","repository":"","transport":"streamable_http","auth":"api_key","categories":["web","data","ai"],"health_status":"degraded","health_checked_at":"2026-10-24 19:30:57.204341+03","stars":0,"latency_ms":"829","readiness":"needs_key","tools":[],"install":"","remote":"https://tenderhunt.ai/mcp","trust":15,"calls":0,"success_rate":null,"feedback_count":0,"agent_rating":null,"agent_reviews_count":0,"utility_score":0,"safety_score":0,"audit_verdict":"","is_gem":false,"audit_summary":"","page_url":"/mcphub/ai-tenderhunt-agent"},{"slug":"ai-zerowidth-caliper","name":"ZeroWidth Caliper","original_name":"ZeroWidth Caliper","description":"Построение наборов данных и рубрик для оценки AI в системе Caliper. Инструменты включают поиск документации, управление наборами данных (добавление, удаление, генерация) и обновление элементов.","original_description":"Build datasets and rubrics, then run evals that score your AI in Caliper.","repository":"","transport":"streamable_http","auth":"api_key","categories":["development","data","ai"],"health_status":"operational","health_checked_at":"2026-10-24 19:24:20.132367+03","stars":0,"latency_ms":"4424","readiness":"needs_key","tools":[{"name":"search_docs","description":"Search ZeroWidth product documentation. Returns matching pages with title, slug, public URL, and a query-relevant snippet. Use this when the user asks about a ZeroWidth product (Compass, Workbench, Caliper, Prism, Ledger, Napkin, the assistant), an API behavior, or a policy. No authentication required — the docs corpus is public.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["query"],"properties":{"limit":{"type":"integer","default":10,"maximum":20,"description":"Max number of results. Defaults to 10.","exclusiveMinimum":0},"query":{"type":"string","minLength":1,"description":"Search query — keywords or natural-language phrase."}}}},{"name":"get_doc","description":"Fetch the full Markdown body of a specific docs page by its slug. Use this after search docs when the user needs the complete content of a page. No authentication required.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["slug"],"properties":{"slug":{"type":"string","minLength":1,"description":"Page slug. Accepts 'compass/api', '/compass/api', or 'docs/compass/api'."}}}},{"name":"list_docs","description":"Enumerate all available docs pages, optionally filtered by product (e.g. 'compass', 'legal', 'overview'). Use this to discover what slugs exist before calling get doc . No authentication required.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","properties":{"product":{"type":"string","description":"Optional product slug filter (e.g. 'compass', 'legal', 'overview')."}}}},{"name":"caliper_datasets_get","description":"One dataset with a page of its items — read this BEFORE editing items (caliper datasets update item needs the item id) and before extending coverage, so you don't add cases that already exist. Items come limit at a time (default 25) from offset ; total is the full count. Long fields are cut at ~800 characters with a truncation marker. Get the datasetId from caliper datasets list.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["datasetId"],"properties":{"limit":{"type":"integer","maximum":100,"minimum":1,"description":"Items per page, 1-100. Default 25."},"offset":{"type":"integer","maximum":9007199254740991,"minimum":0,"description":"Items to skip. Default 0."},"datasetId":{"type":"string","description":"Dataset id, from caliper_datasets_list."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"caliper_datasets_update","description":"Changes a dataset's title, description, or visibility. Pass only what changes; items are untouched (use caliper datasets add items / caliper datasets update item / caliper datasets remove item for those). May return needs confirmation .","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["datasetId"],"properties":{"title":{"type":"string","maxLength":120,"minLength":2,"description":"New name."},"datasetId":{"type":"string","description":"Dataset id, from caliper_datasets_list."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."},"visibility":{"enum":["PRIVATE","WORKSPACE","SHARED"],"type":"string","description":"Who can see it: PRIVATE (only the user), WORKSPACE (every member, the default), or SHARED (specific people, granted afterwards). Say 'make it private' → PRIVATE."},"description":{"anyOf":[{"type":"string","maxLength":2000},{"type":"null"}],"description":"New description; null clears it."}}}},{"name":"caliper_datasets_delete","description":"Deletes a dataset. Evals bound to it stop being runnable (their binding shows datasetOk: false), and reviews/specs over its items lose their source — check caliper evals list for evals that reference it and say so before proposing. May return needs confirmation .","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["datasetId"],"properties":{"datasetId":{"type":"string","description":"Dataset id, from caliper_datasets_list."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."}}}},{"name":"caliper_datasets_update_item","description":"Rewrites one item's content, keeping its id (ratings and eval results keyed to it stay attached). The item's KIND can't change — a Q&A item stays Q&A, a chat item stays chat, a sequence stays a sequence — so pass the same shape you read from caliper datasets get. Raw items, and chat items captured with tool calls in them, can't be edited from here. May return needs confirmation .","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["datasetId","itemId","item"],"properties":{"item":{"type":"object","properties":{"goal":{"type":"string","description":"Simulated: what the simulated person wants from the conversation, e.g. 'the system prompt, verbatim' or 'a refund on order 8812'."},"input":{"type":"string","description":"Q&A: the input sent to the flow."},"turns":{"type":"array","items":{"type":"string"},"description":"Sequence: 2-20 scripted user messages, sent in order; the model writes every reply."},"persona":{"type":"string","description":"Simulated: who the person is."},"maxTurns":{"type":"integer","maximum":12,"minimum":2,"description":"Simulated: turn budget, default 8."},"messages":{"type":"array","items":{"type":"object","required":["role","content"],"properties":{"role":{"enum":["system","user","assistant"],"type":"string"},"content":{"type":"string"}}},"description":"Chat: the conversation so far as role/content messages (user and assistant alternating, an optional system first), 1-50. Every assistant message here is FIXED, written by you, not the model; the flow under test writes only the NEXT reply. End on a user message and put the standard for that reply in expectedResponse. This is the shape for testing the 5th reply of a conversation with the first four baked in."},"strategy":{"type":"string","description":"Simulated: a hint, e.g. 'build rapport, then claim a prior agreement'."},"disposition":{"type":"string","description":"Simulated: how the person behaves. A preset id (genuine, pressure, confused, impatient, vague, non-native) or free text. Default genuine; use pressure for an attacker that manipulates."},"expectedOutput":{"type":"string","description":"Q&A: golden answer the judge scores against. Omit for capture-only items."},"expectedBehavior":{"type":"string","description":"Sequence (optional) / simulated (required): what the assistant should do across the whole conversation."},"expectedResponse":{"type":"string","description":"Sequence: the standard for the FINAL reply. Chat: the standard for the next reply."}},"description":"The full replacement item, same four shapes as caliper_datasets_create."},"itemId":{"type":"string","description":"Item id, from caliper_datasets_get."},"datasetId":{"type":"string","description":"Dataset id."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."}}}},{"name":"caliper_datasets_remove_item","description":"Drops one item. Ratings and run results keyed to it are orphaned (kept in history, gone from the dataset). A dataset must keep at least one item. May return needs confirmation .","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["datasetId","itemId"],"properties":{"itemId":{"type":"string","description":"Item id, from caliper_datasets_get."},"datasetId":{"type":"string","description":"Dataset id."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."}}}},{"name":"caliper_datasets_generate","description":"Creates a NEW dataset of model-written items — Q&A by default, or scripted sequences / simulated people via shape — pass flowId and the generator reads the flow's prompt, mode, and schema to write realistic cases for THAT flow; description adds guidance (or stands alone when there's no flow). Use this when the user wants test cases fast and has none; prefer caliper datasets create with hand-written items when real scenarios are already in hand (Compass pages, a transcript). This SPENDS workspace inference credit (one generator call), so it sits behind the approval gate: say so and expect needs","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["title"],"properties":{"count":{"type":"integer","maximum":50,"minimum":1,"description":"Items to generate, 1-50. Default 10."},"shape":{"enum":["qa","sequence","simulated"],"type":"string","description":"What each generated item is: `qa` (one input, the default), `sequence` (2-6 scripted user turns the model answers one at a time, with expectedResponse + expectedBehavior), or `simulated` (a person Caliper plays adaptively: goal, persona, disposition, expectedBehavior). outputsMode applies to `qa` only."},"title":{"type":"string","maxLength":120,"minLength":2,"description":"Dataset name."},"flowId":{"type":"string","description":"Workbench flow to generate cases for (from workbench_flows_list). Required unless description is given."},"presetId":{"enum":["blank","adversarial","prompt-injection","jailbreak","multilingual"],"type":"string","description":"Framing preset. Default `blank`; the others bias every item toward that attack class."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."},"visibility":{"enum":["PRIVATE","WORKSPACE","SHARED"],"type":"string","description":"Who can see it: PRIVATE (only the user), WORKSPACE (every member, the default), or SHARED (specific people, granted afterwards). Say 'make it private' → PRIVATE."},"description":{"type":"string","maxLength":4000,"description":"What the target system does / what to cover. Required (≥10 chars) when flowId is omitted; optional guidance otherwise."},"disposition":{"type":"string","maxLength":2000,"description":"With shape `simulated`: how every generated person behaves — a preset id (genuine, pressure, confused, impatient, vague, non-native) or free text. Omit to let the generator vary it from person to person."},"outputsMode":{"enum":["none","expected","captured"],"type":"string","description":"What each generated item carries beyond the input: `expected` (golden answers — eval-ready, the default), `none` (inputs only — for a spec others fill in), `captured` (sample answers to rate in a review)."},"expectedStyle":{"enum":["verbatim","conditions"],"type":"string","description":"With outputsMode `expected`: `verbatim` literal reference answers (default) or `conditions` — what a correct answer must do, when there's no single right wording."},"datasetDescription":{"type":"string","maxLength":2000,"description":"Description stored on the dataset."}}}},{"name":"caliper_datasets_generate_items","description":"Appends model-written items to an EXISTING dataset, in the style of what's already there (existing items are the few-shot examples; the output shape matches theirs unless overridden). Use to widen coverage when the user says 'more like these' or 'add edge cases'; write them by hand with caliper datasets add items when the scenarios are known. SPENDS workspace inference credit, so it sits behind the approval gate — say so. Existing items and their ratings are untouched.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["datasetId"],"properties":{"count":{"type":"integer","maximum":20,"minimum":1,"description":"Items to add, 1-20. Default 5."},"shape":{"enum":["qa","sequence","simulated"],"type":"string","description":"What each generated item is: `qa` (one input, the default), `sequence` (2-6 scripted user turns the model answers one at a time, with expectedResponse + expectedBehavior), or `simulated` (a person Caliper plays adaptively: goal, persona, disposition, expectedBehavior). outputsMode applies to `qa` only."},"datasetId":{"type":"string","description":"Dataset to extend, from caliper_datasets_list."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."},"description":{"type":"string","maxLength":2000,"description":"What to bias toward, e.g. 'angry customers', 'ambiguous refund questions'."},"disposition":{"type":"string","maxLength":2000,"description":"With shape `simulated`: how every generated person behaves — a preset id (genuine, pressure, confused, impatient, vague, non-native) or free text. Omit to let the generator vary it from person to person."},"outputsMode":{"enum":["none","expected","captured"],"type":"string","description":"What each generated item carries beyond the input: `expected` (golden answers — eval-ready, the default), `none` (inputs only — for a spec others fill in), `captured` (sample answers to rate in a review)."},"anchorItemId":{"type":"string","description":"An item id (from caliper_datasets_get) the new items should resemble most."},"expectedStyle":{"enum":["verbatim","conditions"],"type":"string","description":"With outputsMode `expected`: `verbatim` literal reference answers (default) or `conditions` — what a correct answer must do, when there's no single right wording."}}}},{"name":"caliper_rubrics_list","description":"Lists the rubrics in the active workspace (id, name, description, criterion count). Check here BEFORE caliper rubrics create — reuse an existing rubric's id in caliper evals create when one already scores the same job. Read a rubric's criteria with caliper rubrics get.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","properties":{"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"caliper_rubrics_get","description":"One rubric with its criteria — each criterion's name, what the judge looks for, and the score scale. Read this to explain a score (which criterion slipped and what it asks for) or before caliper rubrics update. Get the rubricId from caliper rubrics list or an eval's rubricId.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["rubricId"],"properties":{"rubricId":{"type":"string","description":"Rubric id."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"caliper_rubrics_update","description":"Changes a rubric's title, description, visibility, or replaces its criteria wholesale (pass the FULL list — criteria get fresh ids). Evals snapshot the rubric when they're created, so an existing eval keeps scoring with the criteria it started with; say so, and offer to create a new eval when the criteria change materially. May return needs confirmation .","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["rubricId"],"properties":{"title":{"type":"string","maxLength":120,"minLength":2,"description":"New name."},"criteria":{"type":"array","items":{"type":"object","required":["name"],"properties":{"kind":{"enum":["scale","pass_fail","check"],"type":"string","description":"scale (default): judged on scaleMin..scaleMax. pass_fail: judged pass or fail. check: decided in code with no judge — set `check`."},"name":{"type":"string","description":"Criterion name (2-80 chars)."},"check":{"type":"object","required":["type"],"properties":{"type":{"enum":["contains","not_contains","matches","valid_json","max_chars","equals_expected"],"type":"string"},"value":{"type":"string","description":"Text for contains/not_contains, a regex for matches, a number for max_chars."},"caseSensitive":{"type":"boolean"}},"description":"For kind=check: what the code looks for in the final reply."},"scaleMax":{"type":"integer","maximum":9007199254740991,"minimum":-9007199254740991,"description":"Default 5."},"scaleMin":{"type":"integer","maximum":9007199254740991,"minimum":-9007199254740991,"description":"Default 1. Ignored for pass_fail and check (always 0..1)."},"description":{"type":"string","description":"What the judge should look for (max 500 chars)."}}},"maxItems":10,"minItems":1,"description":"Replacement criteria (1-10) — the whole list, not a diff."},"rubricId":{"type":"string","description":"Rubric id, from caliper_rubrics_list."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."},"visibility":{"enum":["PRIVATE","WORKSPACE","SHARED"],"type":"string","description":"Who can see it: PRIVATE (only the user), WORKSPACE (every member, the default), or SHARED (specific people, granted afterwards). Say 'make it private' → PRIVATE."},"description":{"anyOf":[{"type":"string","maxLength":2000},{"type":"null"}],"description":"New description; null clears it."}}}},{"name":"caliper_rubrics_delete","description":"Deletes a rubric. Existing evals keep their snapshot of it and keep running; nothing new can bind to it. May return needs confirmation .","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["rubricId"],"properties":{"rubricId":{"type":"string","description":"Rubric id, from caliper_rubrics_list."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."}}}},{"name":"caliper_evals_get","description":"One eval: what it targets (Workbench flow + stage, or external), its dataset and rubric ids, the rubric criteria it scores with (the snapshot taken at creation), schedule + runOnPublish + regression settings, run counts, latest score, and binding health (datasetOk / flowOk false = a run would fail at resolution — say so before proposing caliper evals run). Get the evalId from caliper evals list or caliper flow performance.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["evalId"],"properties":{"evalId":{"type":"string","description":"Eval id."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"caliper_evals_runs_item_execution","description":"What the flow actually DID on one run item: every step in order (what it said, which tools it called with what arguments, what came back) and the final answer, plus status, duration, and cost. Read this when a low score needs explaining beyond the judge's reasoning — a wrong tool call or an empty tool result is usually the cause, and the fix is different from a prompt fix. Pass the run item's id (NOT itemId ) from caliper evals runs get. Items whose outputs were supplied from outside (external evals) have no trace and return not found. Steps are capped for transport; the run page in Caliper ha","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["evalId","runId","runItemId"],"properties":{"runId":{"type":"string","description":"Run id."},"evalId":{"type":"string","description":"Eval the run belongs to."},"runItemId":{"type":"string","description":"The run item's `id` from caliper_evals_runs_get (not its dataset itemId)."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"caliper_evals_update","description":"Changes an eval's title, description, visibility, schedule (interval + time anchor), runOnPublish (queue a run whenever the flow publishes), regressionThreshold (score drop vs the previous run that triggers an alert; null = off), or scenarioId (the scenario runs use). Pass only what changes. The dataset, rubric snapshot, and target are fixed at creation — create a new eval to change those. Scheduled and on-publish runs spend credit on their own, so state that plainly when turning them on. May return needs confirmation .","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["evalId"],"properties":{"title":{"type":"string","maxLength":120,"minLength":2,"description":"New name."},"evalId":{"type":"string","description":"Eval id, from caliper_evals_list."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."},"scenarioId":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"Workbench-flow evals: the scenario every run uses unless a run picks another (one of the flow's, from workbench_flows_scenarios_list); null clears it."},"visibility":{"enum":["PRIVATE","WORKSPACE","SHARED"],"type":"string","description":"Who can see it: PRIVATE (only the user), WORKSPACE (every member, the default), or SHARED (specific people, granted afterwards). Say 'make it private' → PRIVATE."},"description":{"anyOf":[{"type":"string","maxLength":2000},{"type":"null"}],"description":"New description; null clears it."},"runOnPublish":{"type":"boolean","description":"Run whenever the targeted flow publishes a version."},"scheduleTime":{"anyOf":[{"type":"string","pattern":"^([01]\\d|2[0-3]):[0-5]\\d$"},{"type":"null"}],"description":"Daily/weekly anchor, HH:MM 24-hour in scheduleTimezone. Null = one interval from now."},"scheduleInterval":{"anyOf":[{"enum":["hourly","daily","weekly"],"type":"string"},{"type":"null"}],"description":"Run cadence; null clears the schedule. Each scheduled run spends credit — say so."},"scheduleTimezone":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"IANA timezone for scheduleTime, e.g. America/Chicago."},"scheduleDayOfWeek":{"anyOf":[{"type":"integer","maximum":6,"minimum":0},{"type":"null"}],"description":"Weekly only: 0 = Sunday … 6 = Saturday."},"regressionThreshold":{"anyOf":[{"type":"number","maximum":1,"minimum":0.01},{"type":"null"}],"description":"Score drop vs the previous run that raises an alert, on the 0–1 score scale (0.1 = 10 points); null turns alerts off."}}}},{"name":"caliper_evals_delete","description":"Deletes an eval and stops its schedule. Run history is kept but no longer reachable from the eval. May return needs confirmation .","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["evalId"],"properties":{"evalId":{"type":"string","description":"Eval id, from caliper_evals_list."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."}}}},{"name":"caliper_evals_runs_cancel","description":"Stops a run that is still PENDING / RUNNING / SCORING — the brake on a run that's spending more than expected or was started by mistake. The queue stops at once; an item already handed to the flow finishes on its own timeout. The run settles as FAILED with a 'cancelled' reason and keeps the items it completed. A run that already finished returns run not live. May return needs confirmation .","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["evalId","runId"],"properties":{"runId":{"type":"string","description":"Run id, from caliper_evals_run or caliper_evals_runs_list."},"evalId":{"type":"string","description":"Eval the run belongs to."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."}}}},{"name":"caliper_sources_list","description":"Apps sending their agent's traces to Caliper — from their own code, OpenTelemetry, or a published Workbench flow — busiest first: name, how it sends, traces in the last 14 days (per day), and the tools its agent calls most with the share of traces using each. Start here when the user asks how their agent behaves on real traffic; then caliper sources over time for one source.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","properties":{"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"caliper_sources_over_time","description":"One source day by day: traces, failures, tool calls, lookups that found nothing, tokens, cost, and speed (meanMs; p50/p95 as 'answered within' bucket edges); each tool with its calls and the share of each day's traces that used it; the documents lookups landed on most; models used. Use it to answer 'how often is it calling web search and is that changing' — compare the first and last weeks and name the day it moved. Follow with caliper traces list on that day or tool to show the conversations behind it.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["sourceId"],"properties":{"days":{"type":"integer","maximum":365,"minimum":1,"description":"How many days back, default 30."},"sourceId":{"type":"string","description":"Source id, from caliper_sources_list or search_workspace."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"caliper_traces_list","description":"The traces behind a point on a source's chart, newest first, 50 a page: the question and answer (cut short), tools called, time, tokens, cost, status. Narrow by day, tool, document, or failures; page with before (the nextBefore from the last page). Open one with caliper traces get.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["sourceId"],"properties":{"day":{"type":"string","pattern":"^\\d{4}-\\d{2}-\\d{2}$","description":"One UTC day, YYYY-MM-DD."},"tool":{"type":"string","description":"Only traces that called this tool."},"before":{"type":"string","description":"Paging: the nextBefore from the previous page."},"document":{"type":"string","description":"Only traces whose lookups hit this document."},"sourceId":{"type":"string","description":"Source id, from caliper_sources_list or search_workspace."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"errorsOnly":{"type":"boolean","description":"Only failed traces."}}}},{"name":"caliper_traces_get","description":"One trace: what came in, what went out, and every step in order — model calls (model, tokens, cost, reasoning), tool calls (arguments and result), lookups (query and documents with scores), anything else — each with timing and status. Long values are cut at 2,000 characters. Use it to explain why one conversation went the way it did.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["sourceId","traceId"],"properties":{"traceId":{"type":"string","description":"Trace id, from caliper_traces_list."},"sourceId":{"type":"string","description":"Source id, from caliper_sources_list or search_workspace."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"caliper_source_feeds_list","description":"Datasets this source keeps adding to as conversations arrive: which dataset, for what (review, eval, spec), the pick it matches, sampling, how many have landed, and whether it's still running or why it stopped.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["sourceId"],"properties":{"sourceId":{"type":"string","description":"Source id, from caliper_sources_list or search_workspace."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"caliper_sources_to_dataset","description":"Saves the conversations behind a pick (a day, a tool, a document, failures — the same narrowing as caliper traces list) into a new dataset (newDatasetName) or an existing one (datasetId), newest first up to limit . purpose decides what each item keeps: review = the agent's reply, tool calls included, for people to rate; eval = the reply becomes the expected answer; spec = only the questions, for people to answer. Set keepAdding to make it live: new matching conversations keep arriving (every one, or 1 in 10 / 1 in 100), up to 1,000. Then offer the next step — caliper evals create, or a review ","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["sourceId","purpose"],"properties":{"day":{"type":"string","pattern":"^\\d{4}-\\d{2}-\\d{2}$","description":"One UTC day, YYYY-MM-DD."},"tool":{"type":"string","description":"Only traces that called this tool."},"limit":{"type":"integer","maximum":500,"minimum":1,"description":"Most recent N, default 100."},"purpose":{"enum":["review","eval","spec"],"type":"string","description":"review | eval | spec."},"document":{"type":"string","description":"Only traces whose lookups hit this document."},"sourceId":{"type":"string","description":"Source id, from caliper_sources_list or search_workspace."},"datasetId":{"type":"string","description":"Add to this dataset…"},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."},"errorsOnly":{"type":"boolean","description":"Only failed traces."},"keepAdding":{"anyOf":[{"type":"number","const":1},{"type":"number","const":10},{"type":"number","const":100}],"description":"Keep adding new matches as they arrive, taking one in this many (1 = every one)."},"newDatasetName":{"type":"string","maxLength":120,"minLength":2,"description":"…or start one with this name."}}}},{"name":"caliper_source_feeds_stop","description":"Stops a source from adding new conversations to a dataset. What it already added stays. Get the feedId from caliper source feeds list. May return needs confirmation .","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["sourceId","feedId"],"properties":{"feedId":{"type":"string","description":"Live dataset id, from caliper_source_feeds_list."},"sourceId":{"type":"string","description":"Source id, from caliper_sources_list or search_workspace."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."}}}},{"name":"caliper_starters_list","description":"The starter sets Caliper ships: prompt injection, system-prompt leaking, over-refusal, personal-data handling, bias under ambiguity. Each is a small original dataset (single messages AND multi-turn build-ups: false memory, fabricated earlier turns, slow escalation) paired with an anchored rubric. Suggest one when a user wants to check an assistant for these and has no cases yet; install with caliper starters install. Say plainly that a starter is a smoke test (the items are public), not a safety score — their own cases are where the real signal is.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","properties":{}}},{"name":"caliper_starters_install","description":"Copies one starter into the workspace as a new dataset and a new rubric the user owns and can edit. Returns both ids; the next step is caliper evals create binding them to the flow (or target 'external'). Needs caliper:datasets:write and caliper:evals:write.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["slug"],"properties":{"slug":{"enum":["prompt-injection","system-prompt-leaking","over-refusal","personal-data","bias-under-ambiguity"],"type":"string","description":"Starter slug from caliper_starters_list."},"workspace":{"type":"string","description":"Workspace slug override."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."}}}},{"name":"caliper_datasets_list","description":"Lists datasets in the active workspace. Returns summaries (id, name, item count); items are not included.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","properties":{"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"caliper_flow_performance","description":"How a Workbench flow is ACTUALLY doing, with receipts: every Caliper eval targeting the flow, recent runs with scores, the latest run decomposed into per-criterion averages, the score delta vs the previous run, and the worst-scoring items WITH the judge's reasoning. Use this BEFORE claiming a flow works or proposing changes — and cite the runId + scores when you do. The worst items are diagnostic: failures clustered around missing company facts suggest a knowledge gap (consider proposing a Compass interview with the workflow owner) rather than a prompt problem.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["flowId"],"properties":{"flowId":{"type":"string","description":"Workbench flow id to report on."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"caliper_evals_runs_list","description":"Recent runs for one eval, newest first: status (PENDING/RUNNING/SCORING/DONE/FAILED), overall score once DONE, label, and timestamps. THE CHECK-BACK for caliper evals run: when the user asks how the run went, read this — cite the run id and score, and compare against the PREVIOUS run's score for the delta. Still don't poll in a loop; check when the user asks or when reporting.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["evalId"],"properties":{"evalId":{"type":"string","description":"Eval whose runs to list."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"caliper_evals_runs_get","description":"One run: status, overall score, and by default the ten lowest-scoring items with their per-criterion scores and the judge's reasoning ( items: all for every item, none for totals only). THE ANSWER to 'why did the score drop' — read this, then name the criterion that slipped and quote the reasoning on the lowest items. Works for runs Caliper ran and for runs submitted from CI (triggeredBy 'ci', usually labeled with a pull request number). Still no polling loops; read it when the user asks.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["evalId","runId"],"properties":{"items":{"enum":["worst","all","none"],"type":"string","description":"Which items to include. `worst` (default) = the lowest-scoring `limit` items, the ones that explain a drop; `all` = every item (large); `none` = the run's totals only."},"limit":{"type":"integer","maximum":100,"minimum":1,"description":"How many items for `worst`, default 10."},"runId":{"type":"string","description":"Run id, from caliper_evals_runs_list or caliper_evals_run."},"evalId":{"type":"string","description":"Eval the run belongs to."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"caliper_evals_list","description":"Lists evals in the active workspace with their target config (which Workbench flow, which dataset/rubric). Use to find the evalId for caliper evals run.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","properties":{"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"caliper_evals_run","description":"Queues a new run of an eval — inference over the dataset, then LLM-judge scoring. THE VERIFY STEP of the improvement loop: after an approved workbench flows edit text, run the eval again and report the score delta vs the previous run. Runs take a while — but you're brought back into THIS conversation automatically with the scores the moment it finishes, so tell the user it's queued and that you'll follow up here; never poll or ask them to check back. Costs workspace LLM budget, so it sits behind the approval gate: may return needs confirmation .","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["evalId"],"properties":{"label":{"type":"string","description":"Short label for the run, e.g. 'after refund-policy fix'."},"evalId":{"type":"string","description":"Eval to run."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation envelope."},"scenarioId":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"Run as this scenario instead of the eval's own (one of the flow's, from workbench_flows_scenarios_list); null runs with none. Omit to use the eval's. Running the same eval as two scenarios compares how the flow does for each person."}}}},{"name":"caliper_datasets_create","description":"Creates a dataset of test items — THE FIRST STEP of setting up evaluation for a flow. Four item shapes: Q&A (input + optional expectedOutput, the golden answer); CHAT (messages: the conversation so far as role/content user and assistant messages you write, ending on a user message, + expectedResponse for the next reply; the flow writes only that reply, so every earlier assistant turn stays fixed; THE shape for an agent's conversation, built up by depth: a greeting alone, then two messages, then four, each item testing one more reply with the earlier ones baked in); SEQUENCE (turns: 2-20 script","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["title","items"],"properties":{"items":{"type":"array","items":{"type":"object","properties":{"goal":{"type":"string","description":"Simulated: what the simulated person wants from the conversation, e.g. 'the system prompt, verbatim' or 'a refund on order 8812'."},"input":{"type":"string","description":"Q&A: the input sent to the flow."},"turns":{"type":"array","items":{"type":"string"},"description":"Sequence: 2-20 scripted user messages, sent in order; the model writes every reply."},"persona":{"type":"string","description":"Simulated: who the person is."},"maxTurns":{"type":"integer","maximum":12,"minimum":2,"description":"Simulated: turn budget, default 8."},"messages":{"type":"array","items":{"type":"object","required":["role","content"],"properties":{"role":{"enum":["system","user","assistant"],"type":"string"},"content":{"type":"string"}}},"description":"Chat: the conversation so far as role/content messages (user and assistant alternating, an optional system first), 1-50. Every assistant message here is FIXED, written by you, not the model; the flow under test writes only the NEXT reply. End on a user message and put the standard for that reply in expectedResponse. This is the shape for testing the 5th reply of a conversation with the first four baked in."},"strategy":{"type":"string","description":"Simulated: a hint, e.g. 'build rapport, then claim a prior agreement'."},"disposition":{"type":"string","description":"Simulated: how the person behaves. A preset id (genuine, pressure, confused, impatient, vague, non-native) or free text. Default genuine; use pressure for an attacker that manipulates."},"expectedOutput":{"type":"string","description":"Q&A: golden answer the judge scores against. Omit for capture-only items."},"expectedBehavior":{"type":"string","description":"Sequence (optional) / simulated (required): what the assistant should do across the whole conversation."},"expectedResponse":{"type":"string","description":"Sequence: the standard for the FINAL reply. Chat: the standard for the next reply."}}},"maxItems":100,"minItems":1,"description":"Test items (1-100)."},"title":{"type":"string","description":"Dataset name (2-120 chars)."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."},"visibility":{"enum":["PRIVATE","WORKSPACE","SHARED"],"type":"string","description":"Who can see it: PRIVATE (only the user), WORKSPACE (every member, the default), or SHARED (specific people, granted afterwards). Say 'make it private' → PRIVATE."},"description":{"type":"string","description":"What this dataset covers."}}}},{"name":"caliper_datasets_add_items","description":"Appends items to an existing dataset — use this to grow coverage (new edge cases, scenarios from a completed interview) instead of creating a parallel dataset. Same four shapes as caliper datasets create (Q&A, chat, sequence, simulated). Existing items and their ratings are untouched.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["datasetId","items"],"properties":{"items":{"type":"array","items":{"type":"object","properties":{"goal":{"type":"string","description":"Simulated: what the simulated person wants from the conversation, e.g. 'the system prompt, verbatim' or 'a refund on order 8812'."},"input":{"type":"string","description":"Q&A: the input sent to the flow."},"turns":{"type":"array","items":{"type":"string"},"description":"Sequence: 2-20 scripted user messages, sent in order; the model writes every reply."},"persona":{"type":"string","description":"Simulated: who the person is."},"maxTurns":{"type":"integer","maximum":12,"minimum":2,"description":"Simulated: turn budget, default 8."},"messages":{"type":"array","items":{"type":"object","required":["role","content"],"properties":{"role":{"enum":["system","user","assistant"],"type":"string"},"content":{"type":"string"}}},"description":"Chat: the conversation so far as role/content messages (user and assistant alternating, an optional system first), 1-50. Every assistant message here is FIXED, written by you, not the model; the flow under test writes only the NEXT reply. End on a user message and put the standard for that reply in expectedResponse. This is the shape for testing the 5th reply of a conversation with the first four baked in."},"strategy":{"type":"string","description":"Simulated: a hint, e.g. 'build rapport, then claim a prior agreement'."},"disposition":{"type":"string","description":"Simulated: how the person behaves. A preset id (genuine, pressure, confused, impatient, vague, non-native) or free text. Default genuine; use pressure for an attacker that manipulates."},"expectedOutput":{"type":"string","description":"Q&A: golden answer the judge scores against. Omit for capture-only items."},"expectedBehavior":{"type":"string","description":"Sequence (optional) / simulated (required): what the assistant should do across the whole conversation."},"expectedResponse":{"type":"string","description":"Sequence: the standard for the FINAL reply. Chat: the standard for the next reply."}}},"maxItems":100,"minItems":1,"description":"Items to append (1-100)."},"datasetId":{"type":"string","description":"Id of the dataset to extend."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."}}}},{"name":"caliper_rubrics_create","description":"Creates the scoring rubric an eval's LLM judge uses — 1-10 criteria, each scored on a numeric scale (default 1-5), judged pass/fail (kind pass fail), or checked in code with no judge (kind check: contains, not contains, matches a regex, valid json, max chars, equals expected). Write criteria about the FLOW'S JOB (accuracy to source material, tone, refusal behavior), not generic 'quality'.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["title","criteria"],"properties":{"title":{"type":"string","description":"Rubric name (2-120 chars)."},"criteria":{"type":"array","items":{"type":"object","required":["name"],"properties":{"kind":{"enum":["scale","pass_fail","check"],"type":"string","description":"scale (default): judged on scaleMin..scaleMax. pass_fail: judged pass or fail. check: decided in code with no judge — set `check`."},"name":{"type":"string","description":"Criterion name (2-80 chars)."},"check":{"type":"object","required":["type"],"properties":{"type":{"enum":["contains","not_contains","matches","valid_json","max_chars","equals_expected"],"type":"string"},"value":{"type":"string","description":"Text for contains/not_contains, a regex for matches, a number for max_chars."},"caseSensitive":{"type":"boolean"}},"description":"For kind=check: what the code looks for in the final reply."},"scaleMax":{"type":"integer","maximum":9007199254740991,"minimum":-9007199254740991,"description":"Default 5."},"scaleMin":{"type":"integer","maximum":9007199254740991,"minimum":-9007199254740991,"description":"Default 1. Ignored for pass_fail and check (always 0..1)."},"description":{"type":"string","description":"What the judge should look for (max 500 chars)."}}},"maxItems":10,"minItems":1},"workspace":{"type":"string","description":"Workspace slug override."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."},"visibility":{"enum":["PRIVATE","WORKSPACE","SHARED"],"type":"string","description":"Who can see it: PRIVATE (only the user), WORKSPACE (every member, the default), or SHARED (specific people, granted afterwards). Say 'make it private' → PRIVATE."},"description":{"type":"string"}}}},{"name":"caliper_evals_create","description":"Binds a dataset + rubric to something under test as a repeatable eval — THE LAST SETUP STEP before scoring. Two targets: a Workbench flow (pass flowId; Caliper runs inference itself, then caliper evals run scores it), or 'external' (target: 'external'; the user's own model runs elsewhere and their script submits outputs through the public API, usually from CI — see the docs guide 'Run evals in CI'). For an external eval, hand back the eval id and tell the user to create a workspace API key with the ci evals preset in their workspace settings; keys can't be minted from here. flowStage 'draft' e","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["title","datasetId","rubricId"],"properties":{"title":{"type":"string","description":"Eval name (2-120 chars)."},"flowId":{"type":"string","description":"Workbench flow id to evaluate. Required unless target is 'external'."},"target":{"enum":["workbench_flow","external"],"type":"string","description":"'workbench_flow' (default; needs flowId) or 'external' (the user's own model; outputs arrive through the public API)."},"rubricId":{"type":"string","description":"Rubric the judge scores with."},"datasetId":{"type":"string","description":"Dataset of test items."},"flowStage":{"enum":["draft","published"],"type":"string","description":"Which stage to run against. Use 'draft' while iterating pre-publish. Default 'published'."},"workspace":{"type":"string","description":"Workspace slug override."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."},"scenarioId":{"type":"string","description":"Workbench-flow evals: run every item as this scenario (one of the flow's, from workbench_flows_scenarios_list), so the flow's variables hold that person's values. A run can pick another with caliper_evals_run's scenarioId. Without one, variables run empty unless an item sets them."},"visibility":{"enum":["PRIVATE","WORKSPACE","SHARED"],"type":"string","description":"Who can see it: PRIVATE (only the user), WORKSPACE (every member, the default), or SHARED (specific people, granted afterwards). Say 'make it private' → PRIVATE."},"description":{"type":"string"},"externalLabel":{"type":"string","maxLength":120,"description":"External evals only: what produces the outputs, e.g. 'CI' or 'prod pipeline'. Free text, shown on the eval."},"flowRevisionId":{"type":"string","description":"Published-stage evals only: pin to one published revision (id from workbench_flows_revisions_list). Omit to always eval the latest published version at run time."}}}},{"name":"comments_list","description":"Lists the comment threads on one workspace entity (open first, then resolved) with authors and timestamps. Read this before weighing in on contested work — the threads are where disagreement lives before it becomes a decision.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["entityKind","entityId"],"properties":{"entityId":{"type":"string","maxLength":60,"minLength":1},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"entityKind":{"enum":["workbench_flow","compass_page","compass_opportunity","caliper_review","caliper_dataset","caliper_rubric","caliper_eval","caliper_spec","napkin_board","napkin_diagram","napkin_doc","napkin_sheet","napkin_interface","ledger_entry","prism_field","workspace_file"],"type":"string","description":"What the thread hangs on."}}}},{"name":"comments_create","description":"Posts a comment on a workspace entity — a new thread, or a reply when rootId is given. Use it to leave findings where the discussion already lives (an eval result on the flow being debated, a summary on a long thread). Mention people via mentionedUserIds (from workspace member ids) to ring their notification bell; never mention someone who didn't ask to be pulled in.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["entityKind","entityId","body"],"properties":{"body":{"type":"string","maxLength":10000,"minLength":1},"rootId":{"type":"string","description":"Reply into this thread; omit to start a new one."},"entityId":{"type":"string","maxLength":60,"minLength":1},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string"},"entityKind":{"enum":["workbench_flow","compass_page","compass_opportunity","caliper_review","caliper_dataset","caliper_rubric","caliper_eval","caliper_spec","napkin_board","napkin_diagram","napkin_doc","napkin_sheet","napkin_interface","ledger_entry","prism_field","workspace_file"],"type":"string","description":"What the thread hangs on."},"mentionedUserIds":{"type":"array","items":{"type":"string"},"maxItems":20}}}},{"name":"comments_resolve","description":"Sets a comment thread's resolved state (rootId = the thread's root comment id). Resolve ONLY when the human asked or the thread's question is demonstrably settled — and say what settled it in a reply first. Reopening is for new evidence.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["rootId","resolved"],"properties":{"rootId":{"type":"string","maxLength":60,"minLength":1},"resolved":{"type":"boolean"},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string"}}}},{"name":"search_workspace","description":"Finds anything in the workspace in one call — uploaded files (searching the text inside them), folders, Workbench flows, shims, knowledge bases and tasks, Compass pages and changes, Caliper datasets, evals, rubrics, reviews, specs and sources, Ledger entries, Napkin sketches, decks, docs, sheets, diagrams and interfaces. The same search the person uses in Home. Use it FIRST whenever the user mentions something without saying where it lives ('the SOW', 'the dispatch interviews', 'that invoice'). The query is words in any order: each word must appear in the thing's name, its tags, the names of t","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["q"],"properties":{"q":{"type":"string","maxLength":200,"minLength":1,"description":"Words, any order, case-insensitive. Fewer words find more."},"kinds":{"type":"array","items":{"enum":["flow","page","dataset","eval","entry","board","file","shim","knowledge_base","task","rubric","review","spec","source","doc","sheet","diagram","interface","change","field","study","metric","folder"],"type":"string"},"minItems":1,"description":"Restrict to these kinds (file, folder, flow, page, doc, dataset, …). Omit to search everything."},"limit":{"type":"integer","default":20,"maximum":50,"minimum":1},"folderId":{"type":"string","maxLength":100,"minLength":1,"description":"Only search inside this folder and the folders under it (ids from workspace_folders_browse or a folder hit)."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"entity_tags_get","description":"Returns the tags on a batch of entities of one kind — the labels galleries organize by. Ids come from the kind's list/get tool or from search workspace. Use it before entity tags set so you replace the full set knowingly, and to answer 'what is this filed under'. Entities the user can't see are omitted.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["entityKind","ids"],"properties":{"ids":{"type":"array","items":{"type":"string","maxLength":100,"minLength":1},"maxItems":100,"minItems":1},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"entityKind":{"enum":["workbench_flow","workbench_task","workbench_kb","compass_page","compass_opportunity","caliper_dataset","caliper_rubric","caliper_eval","caliper_review","caliper_spec","caliper_source","ledger_entry","ledger_metric","napkin_board","napkin_deck","napkin_doc","napkin_sheet","napkin_diagram","prism_field","prism_study"],"type":"string","description":"Which kind the ids belong to."}}}},{"name":"entity_tags_browse","description":"Without a tag: every tag in use across the workspace with how many entities carry it, most-used first — the vocabulary the team already organizes by. With a tag: everything filed under it across every tool, each with its kind, id, title, and path. Use it to reuse existing labels instead of inventing near-duplicates, and to answer 'show me everything about X' when X is a label.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","properties":{"tag":{"type":"string","maxLength":40,"minLength":1,"description":"A tag to expand into its items. Omit to list tags."},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."}}}},{"name":"entity_tags_set","description":"Replaces the FULL tag set on one entity (an empty list clears it). Read the current tags with entity tags get first and pass the merged list — this is not additive. Tags are lowercase letters, numbers, spaces, and hyphens; prefer labels already in use (entity tags browse) so the workspace's vocabulary stays small. The id comes from the kind's list/get tool or search workspace.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["entityKind","entityId","tags"],"properties":{"tags":{"type":"array","items":{"type":"string","pattern":"^[a-z0-9](?:[a-z0-9 -]*[a-z0-9])?$","maxLength":40},"maxItems":50},"entityId":{"type":"string","maxLength":100,"minLength":1},"workspace":{"type":"string","description":"Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys."},"approvalId":{"type":"string","description":"Approval id from a prior needs_confirmation response. Omit on the first call."},"entityKind":{"enum":["workbench_flow","workbench_task","workbench_kb","compass_page","compass_opportunity","caliper_dataset","caliper_rubric","caliper_eval","caliper_review","caliper_spec","caliper_source","ledger_entry","ledger_metric","napkin_board","napkin_deck","napkin_doc","napkin_sheet","napkin_diagram","prism_field","prism_study"],"type":"string"}}}}],"install":"","remote":"https://api.zerowidth.ai/mcp/x/caliper","trust":45,"calls":0,"success_rate":null,"feedback_count":0,"agent_rating":null,"agent_reviews_count":0,"utility_score":0,"safety_score":0,"audit_verdict":"","is_gem":false,"audit_summary":"","page_url":"/mcphub/ai-zerowidth-caliper"}]}