{"ok":true,"count":24,"total":2867,"page":1,"pages":120,"per_page":24,"limit":24,"sort":"popular","next_page":2,"gateway":"/mcphub/mcp","note":"Каталог MCP-серверов. Для вызова инструментов агентам — MCP-эндпоинт /mcphub/mcp.","servers":[{"slug":"omniroute","name":"OmniRoute","original_name":"OmniRoute","description":"Шлюз доступа к сотням бесплатных тарифов ИИ-моделей с автоматическим переключением и экономией токенов.","original_description":"Шлюз для доступа к сотням бесплатных тарифов ИИ-моделей с автоматическим переключением и экономией токенов.","repository":"https://github.com/cheaper-inference/OmniRoute","transport":"unknown","auth":"api_key","categories":["ai","development"],"health_status":"unverified","health_checked_at":"2026-10-24 07:33:19.007832+03","stars":80454,"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/omniroute"},{"slug":"headroom","name":"headroom","original_name":"headroom","description":"Сжимает контекст (логи, файлы, ответы) перед отправкой в LLM для сохранения точности ответов.","original_description":"Сервер для сжатия контекста (логи, файлы, ответы) перед отправкой в LLM, сохраняя точность ответов.","repository":"https://github.com/headroomlabs-ai/headroom","transport":"stdio","auth":"unknown","categories":["ai","development"],"health_status":"unverified","health_checked_at":"2026-10-24 07:33:20.182451+03","stars":77672,"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/headroom"},{"slug":"context7","name":"Документация для AI-агентов","original_name":"context7","description":"Предоставляет актуальную документацию и примеры кода из официальных источников прямо в контекст AI-агента. Устраняет галлюцинации и устаревшие данные при разработке.","original_description":"Предоставляет актуальную документацию и примеры кода из официальных источников прямо в контекст AI-агента. Устраняет галлюцинации и устаревшие данные при разработке.","repository":"https://github.com/upstash/context7","transport":"streamable_http","auth":"api_key","categories":["development","ai"],"health_status":"operational","health_checked_at":"2026-10-24 19:40:50.040211+03","stars":63562,"latency_ms":"1577","readiness":"needs_key","tools":[{"name":"resolve-library-id","description":"Resolves a package/product name to a Context7-compatible library ID and returns matching libraries. You MUST call this function before 'Query Documentation' tool to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query. Each result includes: - Library ID: Context7-compatible identifier (format: /org/project) - Name: Library or package name - Description: Short summary - Code Snippets: Number of available code examples - Source Reputation: Authority indicator (High, Medium, Low, or Unk","inputSchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["query","libraryName"],"properties":{"query":{"type":"string","description":"What to look up in the library's documentation. This is used to rank library results by relevance to what the user is trying to accomplish. The query is sent to the Context7 API for processing. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query."},"libraryName":{"type":"string","description":"Library name to search for and retrieve a Context7-compatible library ID. Use the official library name with proper punctuation — e.g., 'Next.js' instead of 'nextjs', 'Customer.io' instead of 'customerio', 'Three.js' instead of 'threejs'."}}}},{"name":"query-docs","description":"Retrieves and queries up-to-date documentation and code examples from Context7 for any programming library or framework. You must call 'Resolve Context7 Library ID' tool first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query. Do not call this tool more than 3 times per question. If you know the programming language the user is working in, pass it as language so the results match their setup.","inputSchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["libraryId","query"],"properties":{"query":{"type":"string","description":"What to look up in the library's documentation, scoped to a single concept. Be specific and include relevant details, but keep each query to one topic — if the user's question spans multiple distinct concepts, make a separate call per concept instead of combining them, unless the question is about how the concepts interact. Good: 'How to set up authentication with JWT in Express.js' or 'React useEffect cleanup function examples'. Bad (too vague): 'auth' or 'hooks'. Bad (too broad): 'routing and auth and caching in Next.js'. The query is sent to the Context7 API for processing. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query."},"language":{"type":"string","description":"Programming language the user is writing code in, such as 'Python', 'TypeScript', 'Go', or 'C#'. Ranks code examples in that language first. Leave it out when the language is unknown or does not apply."},"libraryId":{"type":"string","description":"Exact Context7-compatible library ID (e.g., '/mongodb/docs', '/vercel/next.js', '/supabase/supabase', '/vercel/next.js/v16.2.9') retrieved from 'resolve-library-id' or directly from user query in the format '/org/project' or '/org/project/version'."}}}}],"install":"","remote":"https://mcp.context7.com/mcp","trust":95,"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/context7"},{"slug":"trendradar","name":"TrendRadar","original_name":"TrendRadar","description":"Система мониторинга трендов и общественного мнения с AI-анализом новостей. Нужна для сбора данных, фильтрации шума и получения инсайтов.","original_description":"Система мониторинга трендов и общественного мнения с AI-анализом новостей. Нужна для сбора данных, фильтрации шума и получения инсайтов.","repository":"https://github.com/sansan0/TrendRadar","transport":"unknown","auth":"none","categories":["data","ai","research"],"health_status":"unverified","health_checked_at":"2026-10-23 16:42:51.037816+03","stars":63134,"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/trendradar"},{"slug":"chrome-devtools-mcp","name":"Chrome DevTools MCP","original_name":"Chrome DevTools MCP","description":"Инструменты Chrome DevTools для coding agents.","original_description":"Инструменты Chrome DevTools для coding agents.","repository":"https://github.com/ChromeDevTools/chrome-devtools-mcp","transport":"unknown","auth":"unknown","categories":["web","ai"],"health_status":"unverified","health_checked_at":"2026-10-23 16:21:26.974449+03","stars":54027,"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/chrome-devtools-mcp"},{"slug":"nanobot","name":"nanobot","original_name":"nanobot","description":"Легковесный фреймворк для создания собственных AI-агентов с поддержкой памяти, инструментов и интеграции в чаты. Позволяет агентам работать с файлами и выполнять задачи.","original_description":"Легковесный фреймворк для создания собственных AI-агентов с поддержкой памяти, инструментов и интеграции в чаты. Позволяет агентам работать с файлами и выполнять задачи.","repository":"https://github.com/HKUDS/nanobot","transport":"unknown","auth":"unknown","categories":["ai","productivity"],"health_status":"unverified","health_checked_at":"2026-10-23 17:47:31.230815+03","stars":49300,"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/nanobot"},{"slug":"codebase-memory-mcp","name":"codebase-memory-mcp","original_name":"codebase-memory-mcp","description":"Локальная интеллектуальная система кода для разработчиков и AI-агентов, соединяющая код, документацию и инфраструктуру в постоянный граф.","original_description":"Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware test selection.","repository":"https://github.com/DeusData/codebase-memory-mcp","transport":"unknown","auth":"none","categories":["ai","development","data"],"health_status":"unverified","health_checked_at":"2026-10-24 09:42:12.458587+03","stars":47369,"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/codebase-memory-mcp"},{"slug":"librechat","name":"Open-Source чат с AI и MCP","original_name":"LibreChat","description":"Это платформа для общения с языковыми моделями, поддерживающая интеграцию через протокол MCP. Позволяет пользователям использовать различные модели и расширять функционал с помощью агентов.","original_description":"Это платформа для общения с языковыми моделями, поддерживающая интеграцию через протокол MCP. Позволяет пользователям использовать различные модели и расширять функционал с помощью агентов.","repository":"https://github.com/LibreChat-AI/LibreChat","transport":"unknown","auth":"unknown","categories":["ai"],"health_status":"unverified","health_checked_at":"2026-10-24 07:33:21.380294+03","stars":46232,"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/librechat"},{"slug":"next-ai-draw-io","name":"next-ai-draw-io","original_name":"next-ai-draw-io","description":"Генерирует и редактирует диаграммы draw.io по текстовым описаниям с помощью ИИ. Позволяет создавать схемы архитектуры, ER-диаграммы и процессы прямо в редакторе.","original_description":"Генерирует и редактирует диаграммы draw.io по текстовым описаниям с помощью ИИ. Позволяет создавать схемы архитектуры, ER-диаграммы и процессы прямо в редакторе.","repository":"https://github.com/DayuanJiang/next-ai-draw-io","transport":"streamable_http","auth":"api_key","categories":["development","ai"],"health_status":"offline","health_checked_at":"2026-11-18 12:39:03.460121+03","stars":36388,"latency_ms":"2870","readiness":"needs_key","tools":[],"install":"npx -y @next-ai-drawio/mcp-server@0.4.6","remote":"https://next-ai-drawio.jiang.jp/en/mcp","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/next-ai-draw-io"},{"slug":"context-mode","name":"context-mode","original_name":"context-mode","description":"Оптимизирует контекстное окно ИИ-агентов, изолируя сырые данные в песочнице и сохраняя состояние сессий. Снижает потребление токенов на 98%.","original_description":"Оптимизирует контекстное окно ИИ-агентов, изолируя сырые данные в песочнице и сохраняя состояние сессий. Снижает потребление токенов на 98%.","repository":"https://github.com/mksglu/context-mode","transport":"unknown","auth":"none","categories":["development","ai"],"health_status":"unverified","health_checked_at":"2026-10-23 16:42:55.037359+03","stars":31923,"latency_ms":null,"readiness":"needs_install","tools":[],"install":"","remote":"","trust":75,"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/context-mode"},{"slug":"fastmcp","name":"fastmcp","original_name":"fastmcp","description":"Стандартный фреймворк для создания серверов и клиентов MCP на Python. Автоматически генерирует схемы инструментов и управляет жизненным циклом протокола.","original_description":"Стандартный фреймворк для создания серверов и клиентов MCP на Python. Автоматически генерирует схемы инструментов и управляет жизненным циклом протокола.","repository":"https://github.com/PrefectHQ/fastmcp","transport":"unknown","auth":"unknown","categories":["development","ai"],"health_status":"unverified","health_checked_at":"2026-10-23 17:47:32.410441+03","stars":28182,"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/fastmcp"},{"slug":"n8n-mcp","name":"n8n-mcp","original_name":"n8n-mcp","description":"MCP для Claude Desktop / Claude Code / Windsurf / Cursor, позволяющий строить рабочие процессы n8n.","original_description":"A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you","repository":"https://github.com/czlonkowski/n8n-mcp","transport":"stdio","auth":"api_key","categories":["development","ai"],"health_status":"unverified","health_checked_at":"2026-10-24 09:42:13.471488+03","stars":23126,"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/n8n-mcp"},{"slug":"douyin-tiktok-download-api","name":"Douyin_TikTok_Download_API","original_name":"Douyin_TikTok_Download_API","description":"API для сбора данных и скачивания видео без водяных знаков с Douyin, TikTok и Bilibili, поддерживает вызовы от AI-агентов через MCP.","original_description":"Самостоятельный API для сбора данных и скачивания видео без водяных знаков с Douyin, TikTok и Bilibili. Поддерживает вызовы от AI-агентов через MCP и офлайн-распознавание речи.","repository":"https://github.com/Evil0ctal/Douyin_TikTok_Download_API","transport":"unknown","auth":"api_key","categories":["data","ai"],"health_status":"unverified","health_checked_at":"2026-10-23 16:43:00.20748+03","stars":20856,"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/douyin-tiktok-download-api"},{"slug":"funasr","name":"FunASR","original_name":"FunASR","description":"Открытый инструмент распознавания речи с поддержкой потоковой обработки, диалогов и эмоций для интеграции с AI-агентами.","original_description":"Открытый инструмент для распознавания речи с поддержкой потоковой обработки, диалогов и эмоций. Работает как MCP-сервер для интеграции с AI-агентами.","repository":"https://github.com/modelscope/FunASR","transport":"stdio","auth":"api_key","categories":["ai"],"health_status":"unverified","health_checked_at":"2026-10-23 16:43:01.558867+03","stars":20800,"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/funasr"},{"slug":"mcp-for-beginners","name":"MCP for Beginners","original_name":"mcp-for-beginners","description":"Открытый учебный курс по основам Model Context Protocol (MCP) с примерами на .NET, Java, TypeScript, JavaScript, Rust и Python. Фокусируется на практических техниках создания модульных AI-процессов.","original_description":"This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration.","repository":"https://github.com/microsoft/mcp-for-beginners","transport":"unknown","auth":"none","categories":["ai","development","security"],"health_status":"unverified","health_checked_at":"2026-10-24 09:42:14.078893+03","stars":17505,"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/mcp-for-beginners"},{"slug":"xerj","name":"xerj","original_name":"xerj","description":"Локальный поисковый движок и сервер для индексации кода, логов и документов. Ускоряет работу AI-агентов за счет быстрого поиска контекста без чтения всех файлов.","original_description":"Локальный поисковый движок и сервер для индексации кода, логов и документов. Ускоряет работу AI-агентов за счет быстрого поиска контекста без чтения всех файлов.","repository":"https://github.com/xerj-org/xerj","transport":"unknown","auth":"none","categories":["development","ai"],"health_status":"unverified","health_checked_at":"2026-10-23 17:47:23.43589+03","stars":13622,"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/xerj"},{"slug":"ida-pro-mcp","name":"IDA Pro MCP","original_name":"ida-pro-mcp","description":"AI-powered reverse engineering assistant, который связывает IDA Pro с языковыми моделями через MCP.","original_description":"AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.","repository":"https://github.com/mrexodia/ida-pro-mcp","transport":"stdio","auth":"unknown","categories":["ai"],"health_status":"unverified","health_checked_at":"2026-10-24 09:42:15.08446+03","stars":13124,"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/ida-pro-mcp"},{"slug":"apify-mcp-server","name":"Apify MCP Server","original_name":"Apify MCP Server","description":"Связывает AI-агентов с Apify Actors для работы с веб-данными и автоматизации.","original_description":"Связка AI-агентов с Apify Actors для веб-данных и автоматизации.","repository":"https://github.com/apify/apify-mcp-server","transport":"unknown","auth":"unknown","categories":["web","ai","media"],"health_status":"unverified","health_checked_at":"2026-10-24 10:38:56.01738+03","stars":12862,"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/apify-mcp-server"},{"slug":"fastapi-mcp","name":"fastapi_mcp","original_name":"fastapi_mcp","description":"Превращает endpoints FastAPI в инструменты для MCP, позволяя LLM взаимодействовать с API. Использует встроенную аутентификацию приложения.","original_description":"Превращает endpoints FastAPI в инструменты для MCP, позволяя LLM взаимодействовать с вашими API. Встроенная аутентификация использует существующие зависимости безопасности приложения.","repository":"https://github.com/tadata-org/fastapi_mcp","transport":"streamable_http","auth":"api_key","categories":["development","ai"],"health_status":"offline","health_checked_at":"2026-11-18 12:38:02.412588+03","stars":12024,"latency_ms":null,"readiness":"needs_key","tools":[],"install":"","remote":"https://app.base.url/mcp","trust":65,"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/fastapi-mcp"},{"slug":"pal-mcp-server","name":"PAL MCP Server","original_name":"PAL MCP Server","description":"Объединяет несколько языковых моделей в единый рабочий процесс для разработки. Нужен разработчикам, желающим использовать сильные стороны разных AI одновременно.","original_description":"Объединяет несколько языковых моделей (Claude, Gemini, GPT и др.) в единый рабочий процесс для разработки. Нужен разработчикам, желающим использовать сильные стороны разных AI одновременно.","repository":"https://github.com/BeehiveInnovations/pal-mcp-server","transport":"unknown","auth":"unknown","categories":["development","ai"],"health_status":"unverified","health_checked_at":"2026-10-23 17:55:30.809877+03","stars":11803,"latency_ms":null,"readiness":"needs_install","tools":[],"install":"","remote":"","trust":60,"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/pal-mcp-server"},{"slug":"mcp-use","name":"MCP Use","original_name":"mcp-use","description":"Полноценный фреймворк MCP для разработки приложений для ChatGPT / Claude и серверов MCP для AI-агентов.","original_description":"The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.","repository":"https://github.com/mcp-use/mcp-use","transport":"stdio","auth":"none","categories":["ai","development"],"health_status":"unverified","health_checked_at":"2026-10-24 09:42:16.083429+03","stars":10805,"latency_ms":null,"readiness":"needs_install","tools":[],"install":"npx -y create-mcp-use-app@2.1.0","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/mcp-use"},{"slug":"windows-mcp","name":"Windows-MCP","original_name":"Windows-MCP","description":"Позволяет AI-агентам взаимодействовать с интерфейсом Windows: управлять окнами, приложениями и элементами UI. Необходим для автоматизации задач на ПК без использования компьютерного зрения.","original_description":"Позволяет AI-агентам взаимодействовать с интерфейсом Windows: управлять окнами, приложениями и элементами UI. Необходим для автоматизации задач на ПК без использования компьютерного зрения.","repository":"https://github.com/CursorTouch/Windows-MCP","transport":"stdio","auth":"none","categories":["ai","development","productivity"],"health_status":"unverified","health_checked_at":"2026-10-23 16:42:45.549328+03","stars":10099,"latency_ms":null,"readiness":"needs_install","tools":[],"install":"uvx --from windows-mcp==0.8.8 serve","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/windows-mcp"},{"slug":"mcp","name":"MCP-серверы AWS","original_name":"mcp","description":"Набор официальных серверов для интеграции AI-агентов с сервисами AWS. Дает доступ к документации, инструментам разработки и управлению инфраструктурой.","original_description":"Open source MCP Servers for AWS","repository":"https://github.com/awslabs/mcp","transport":"streamable_http","auth":"none","categories":["development","ai","cloud"],"health_status":"offline","health_checked_at":"2026-11-18 12:38:57.658429+03","stars":9822,"latency_ms":"2274","readiness":"broken","tools":[],"install":"","remote":"https://scorecard.dev/viewer/?uri=github.com/awslabs/mcp","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/mcp"},{"slug":"dashboard-icons","name":"Dashboard Icons MCP","original_name":"dashboard-icons","description":"Дает доступ к коллекции из 3400+ иконок для интерфейсов агентов. Позволяет автоматически подбирать визуальные элементы по названиям сервисов или выполнять поиск по категориям.","original_description":"Предоставляет доступ к коллекции из 3400+ иконок для интерфейсов агентов через MCP. Позволяет автоматически подбирать визуальные элементы для сервисов в конфигурациях.","repository":"https://github.com/homarr-labs/dashboard-icons","transport":"streamable_http","auth":"none","categories":["media","ai"],"health_status":"operational","health_checked_at":"2026-10-24 16:36:08.391153+03","stars":8920,"latency_ms":"829","readiness":"stale","tools":[{"name":"match_icons","description":"Find the best icon for each of up to 50 service names in one call, e.g. a whole homelab or docker-compose stack. Names, slugs and aliases are matched ignoring case, spaces and punctuation ('Pi-hole' = 'pihole'); otherwise the first 10 unmatched names fall back to fuzzy search and typo tolerance. Use this first whenever you have more than one name. Set include details=true when formats, variants or licenses are requested: every best match includes its available urls and license, keeping all previews in one result. Use those returned URLs without calling get icon again or deriving paths from pre","inputSchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["services","context","llm_model"],"properties":{"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"sources":{"type":"array","items":{"enum":["native","selfhst","lobehub","simpleicons"],"type":"string"},"description":"Only search these sources. Default: all. native = dashboardicons.com, then selfh.st, LobeHub (AI brands), Simple Icons."},"services":{"type":"array","items":{"type":"string","maxLength":100},"maxItems":50,"minItems":1,"description":"Service or app names as the user wrote them, e.g. ['Plex', 'Home Assistant', 'Pi-hole', 'qBittorrent']"},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."},"include_details":{"type":"boolean","default":false,"description":"Include each best match's available format/variant URLs and license in this batch"}}}},{"name":"search_icons","description":"Fuzzy-search icons by name, alias or category across dashboardicons.com and the selfh.st, LobeHub and Simple Icons catalogs, best match first (native icons win ties). Queries also match dashboardicons.com Variant names and synonyms: 'light'/'white'/'for dark background', 'dark'/'black', 'wordmark'/'text logo' and Custom variant names such as '4k'. The parent icon is returned and matched variant says which Variant matched. Use it for one vague or partial name, or to explore options. For a list of known services use match icons instead: one call for all of them. Each result's preview url is a re","inputSchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["query","context","llm_model"],"properties":{"limit":{"type":"integer","default":20,"maximum":50,"minimum":1},"query":{"type":"string","maxLength":100,"minLength":1,"description":"A service, brand or app name, alias or category, optionally with a Variant, e.g. 'jellyfin', 'password manager', 'github white' or 'helix wordmark'"},"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"sources":{"type":"array","items":{"enum":["native","selfhst","lobehub","simpleicons"],"type":"string"},"description":"Only search these sources. Default: all. native = dashboardicons.com, then selfh.st, LobeHub (AI brands), Simple Icons."},"category":{"type":"string","maxLength":50,"description":"Only icons in this category (names from list_categories)"},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}},{"name":"get_icon","description":"Get everything about one icon: CDN URLs for every available format (svg, png, webp) and every Variant (default, light, dark, wordmarks and Custom variants such as '4k'), aliases, categories, and license/attribution for external sources. Use it after search icons or match icons, or directly with a slug. Names are resolved loosely ('lm-studio' finds 'lmstudio'; resolved from tells you). An unknown name is not an error: it returns found: false with did you mean suggestions to retry with. Use get icon svg instead when you need the SVG markup itself.","inputSchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["name","context","llm_model"],"properties":{"name":{"type":"string","maxLength":80,"minLength":1,"description":"Icon slug from search_icons or match_icons, e.g. 'home-assistant'. Loose names like 'LM Studio' or 'lm-studio' are resolved."},"source":{"enum":["native","selfhst","lobehub","simpleicons"],"type":"string","description":"Catalog to read from when the same slug exists in several. Default: native first, then selfhst, lobehub, simpleicons."},"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}},{"name":"get_icon_svg","description":"Get the raw SVG markup of one icon, to inline in code, a README or a config file. When the SVG is available the text result is the markup itself. When it is not, reason explains why and url is given when one exists. Names are resolved like get icon, and unknown names return did you mean. Prefer the CDN URLs from get icon when a URL is enough.","inputSchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["name","context","llm_model"],"properties":{"name":{"type":"string","maxLength":80,"minLength":1,"description":"Icon slug from search_icons or match_icons, e.g. 'home-assistant'. Loose names like 'LM Studio' or 'lm-studio' are resolved."},"theme":{"enum":["default","light","dark"],"type":"string","default":"default","description":"'light' is the light-coloured Variant for dark backgrounds and 'dark' the Variant for light backgrounds, when the icon has them"},"source":{"enum":["native","selfhst","lobehub","simpleicons"],"type":"string","description":"Catalog to read from when the same slug exists in several. Default: native first, then selfhst, lobehub, simpleicons."},"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}},{"name":"browse_icons","description":"Page through icons without a search term: everything in a category, one source's catalog, or the newest additions (sort: 'newest'). Use search icons or match icons instead when you know what you are looking for.","inputSchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["context","llm_model"],"properties":{"sort":{"enum":["alphabetical","newest"],"type":"string","default":"alphabetical"},"limit":{"type":"integer","default":50,"maximum":100,"minimum":1},"cursor":{"type":"string","maxLength":20,"description":"next_cursor from the previous page"},"source":{"enum":["native","selfhst","lobehub","simpleicons"],"type":"string","description":"Only icons from this source. Default: all, dashboardicons.com icons first."},"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"category":{"type":"string","maxLength":50,"description":"A category name from list_categories"},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}},{"name":"list_categories","description":"List icon categories with how many icons each has. Use a category name with browse icons to see every icon in it, or as the category filter of search icons.","inputSchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["context","llm_model"],"properties":{"source":{"enum":["native","selfhst","lobehub","simpleicons"],"type":"string","description":"Only count icons from this source. Default: all sources."},"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}},{"name":"submit_icon","description":"Submit one Icon with its required Base svg and all optional well-known and Custom inline SVG Variants in one call per Icon. Never split Variants into separate Submissions or variant slugs. Needs the user to sign in to this MCP server. Signed-in account calls allow at most 512 KiB for the complete encoded JSON body (including escaping and MCP fields), and each SVG is capped at 48 KiB UTF-8. A rejection is not final: fix the files and resubmit the same slug to return your rejected Submission to pending in place. Resubmission replaces the FULL file set: include Base and ALL Variants to keep; omit","inputSchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["name","svg","context","llm_model"],"properties":{"svg":{"type":"string","minLength":1,"description":"Required colour Base SVG, from <svg xmlns=\"http://www.w3.org/2000/svg\" ...> to </svg>. At most 48 KiB UTF-8."},"name":{"type":"string","pattern":"^[a-z0-9]+(-[a-z0-9]+)*$","maxLength":80,"minLength":1,"description":"Icon slug: lowercase letters, digits and single hyphens, e.g. 'my-app'. Becomes the file name. Reuse your rejected Submission's slug to resubmit it in place."},"aliases":{"type":"array","items":{"type":"string","maxLength":80,"minLength":1},"maxItems":20,"description":"Other names people search for, e.g. 'Plex Media Server'"},"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"variants":{"type":"object","properties":{"dark":{"type":"string","minLength":1,"description":"Dark-coloured icon for light backgrounds"},"light":{"type":"string","minLength":1,"description":"Light-coloured icon for dark backgrounds"},"custom":{"type":"object","description":"Custom variant name to inline SVG, e.g. { '4k': '<svg ...>...</svg>' }. Names are lowercase kebab-case, at most 32 characters, and cannot be well-known Variant names or collide with another Icon.","propertyNames":{"type":"string"},"additionalProperties":{"type":"string","minLength":1,"description":"Complete inline SVG markup; at most 48 KiB of UTF-8 per SVG, including Base. No scripts, event handlers, foreignObject, external references or embedded raster images."}},"wordmark":{"type":"string","minLength":1,"description":"Colour brand name"},"wordmark_dark":{"type":"string","minLength":1,"description":"Dark-coloured brand name for light backgrounds"},"wordmark_light":{"type":"string","minLength":1,"description":"Light-coloured brand name for dark backgrounds"}},"description":"All optional Variants for this Icon in the same call. Resubmission replaces the full file set: include every Variant to keep; omitted optional Variants are removed. Supply this object explicitly when resubmitting an Icon with optional or unresolved files; use {} to intentionally remove them all. Never submit separate variant slugs. The complete encoded JSON request, including escaping and MCP fields, must fit within 512 KiB.","additionalProperties":false},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"categories":{"type":"array","items":{"enum":["automation","cloud","database","development","entertainment","finance","gaming","home-automation","media","monitoring","network","security","social","storage","tools","utility"],"type":"string"},"maxItems":16},"description":{"type":"string","maxLength":2000,"description":"What the icon represents, for the reviewers"},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}},{"name":"propose_icon_update","description":"Propose changes to one existing published or community Icon for maintainer review, not direct publication. Needs the user to sign in to this MCP server; only propose changes the user asked for and has the right to share. Optional svg replaces Base; variants adds or replaces well-known and Custom inline SVGs in the same shape as submit icon. Omitted files are preserved; remove explicitly lists { key, note? } objects for optional Variants to delete, never Base, with an optional per-Variant reason for reviewers. aliases and categories are FINAL desired lists: omit to preserve, [] to clear. Each S","inputSchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["name","context","llm_model"],"properties":{"svg":{"type":"string","minLength":1,"description":"Optional replacement Base SVG, at most 48 KiB UTF-8. Omit to keep Base; Base cannot be removed."},"name":{"type":"string","pattern":"^[a-z0-9]+(-[a-z0-9]+)*$","maxLength":80,"minLength":1,"description":"Exact slug of the existing published or community Icon to update. Use search_icons to find published slugs."},"remove":{"type":"array","items":{"type":"object","required":["key"],"properties":{"key":{"anyOf":[{"enum":["light","dark","wordmark","wordmark_light","wordmark_dark"],"type":"string"},{"type":"string","pattern":"^custom:[\\s\\S]{0,}$"}],"description":"Optional Variant key; Base cannot be removed"},"note":{"type":"string","description":"Optional reason for removing this Variant, shown to reviewers"}},"additionalProperties":false},"maxItems":99,"description":"Explicit optional Variant removals as { key, note? }, e.g. [{ key: 'custom:4k', note: 'Obsolete artwork' }]. Keys: light, dark, wordmark, wordmark_light, wordmark_dark or custom:<name>. Base cannot be removed. List each key once and do not also supply its SVG. Do not send file, destination or action; the server resolves the existing file."},"aliases":{"type":"array","items":{"type":"string","maxLength":80,"minLength":1},"maxItems":20,"description":"FINAL desired alias list, not additions only. Omit to preserve current aliases; [] explicitly removes all aliases."},"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"variants":{"type":"object","properties":{"dark":{"type":"string","minLength":1,"description":"Dark-coloured icon for light backgrounds"},"light":{"type":"string","minLength":1,"description":"Light-coloured icon for dark backgrounds"},"custom":{"type":"object","description":"Custom variant name to inline SVG, e.g. { '4k': '<svg ...>...</svg>' }. Names are lowercase kebab-case, at most 32 characters, and cannot be well-known Variant names or collide with another Icon.","propertyNames":{"type":"string"},"additionalProperties":{"type":"string","minLength":1,"description":"Complete inline SVG markup; at most 48 KiB of UTF-8 per SVG, including Base. No scripts, event handlers, foreignObject, external references or embedded raster images."}},"wordmark":{"type":"string","minLength":1,"description":"Colour brand name"},"wordmark_dark":{"type":"string","minLength":1,"description":"Dark-coloured brand name for light backgrounds"},"wordmark_light":{"type":"string","minLength":1,"description":"Light-coloured brand name for dark backgrounds"}},"description":"Only Variant additions or replacements, using the same shape as submit_icon. Omitted Variants are preserved, NOT removed. Existing keys are replaced; new keys are added. Each SVG is at most 48 KiB UTF-8. The complete encoded JSON request must fit within 512 KiB.","additionalProperties":false},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"categories":{"type":"array","items":{"enum":["automation","cloud","database","development","entertainment","finance","gaming","home-automation","media","monitoring","network","security","social","storage","tools","utility"],"type":"string"},"maxItems":16,"description":"FINAL desired category list, not additions only. Omit to preserve current categories; [] explicitly removes all categories."},"description":{"type":"string","maxLength":2000,"description":"Explain the proposed changes to reviewers; does not replace the target Icon's description."},"submission_id":{"type":"string","pattern":"^[a-z0-9]{15}$","description":"Community Submission id when targeting a pending or approved community Icon instead of the published catalog. Must match name."},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}},{"name":"list_my_submissions","description":"List the icons the signed-in user submitted to dashboardicons.com, newest first, with their review status and reviewer comments. Use it to check on icons sent with submit icon or on the website. Needs the user to sign in to this MCP server.","inputSchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["context","llm_model"],"properties":{"limit":{"type":"integer","default":20,"maximum":50,"minimum":1},"status":{"enum":["pending","approved","rejected","added_to_collection"],"type":"string","description":"Only this state: pending (awaiting review), approved (accepted, not published yet), added_to_collection (published), rejected (not final; fix and resubmit)"},"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}},{"name":"get_more_tools","description":"Check for additional tools whenever your task might benefit from specialized capabilities - even if existing tools could work as a fallback.","inputSchema":{"type":"object","required":["context","llm_model"],"properties":{"context":{"type":"string","description":"A description of your goal and what kind of tool would help accomplish it."},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}}],"install":"","remote":"https://dashboardicons.com/api/mcp","trust":100,"calls":16,"success_rate":100,"feedback_count":0,"agent_rating":null,"agent_reviews_count":0,"utility_score":92,"safety_score":93,"audit_verdict":"gem","is_gem":true,"audit_summary":"Сервер выступает в роли надежного визуального ассистента для ИИ-агентов, обеспечивая точную генерацию UI-элементов без галлюцинаций и ошибок лицензирования. Живой тест подтвердил высокую скорость отклика (529 мс) и корректность возврата структурированных данных с прямыми ссылками на ресурсы. Благодаря отсутствию инъекций и чистым схемам, сервер полностью безопасен для интеграции в рабочие процессы разработки.","page_url":"/mcphub/dashboard-icons"}]}