Вход

Not Human Search

Удалённый MCP

Поиск веб-сайтов и сервисов, пригодных для работы AI-агентов. Оценивает готовность сайтов к агентному использованию по 7 сигналам (llms.txt, OpenAPI, MCP серверы) и позволяет проверять конкретные URL.

давно не проверялся схема сломана Удалённый · Streamable HTTP Без авторизации Веб и поиск ИИ и модели Официальный реестр · 7 просмотров

Что умеет

Поиск веб-сайтов и сервисов, пригодных для работы AI-агентов. Оценивает готовность сайтов к агентному использованию по 7 сигналам (llms.txt, OpenAPI, MCP серверы) и позволяет проверять конкретные URL.

Перевод каталога (LLM) · показать оригинал автора

Search the agentic web. 4,100+ sites, 11 tools incl. check url + verify mcp for probe-before-use.

Подключение

Удалённый сервер: клиент обращается по адресу, код на вашей машине не запускается.

Claude Desktop

claude_desktop_config.json

Cursor

~/.cursor/mcp.json

Windsurf

~/.codeium/windsurf/mcp_config.json

Вставьте блок mcpServers в файл конфигурации своего клиента. Ключи не входят в файл: вместо SET_LOCALLY подставьте свои значения.

{
    "mcpServers": {
        "ai-nothumansearch-search": {
            "url": "https://nothumansearch.ai/mcp"
        }
    }
}

Вызов без установки — через шлюз

Агент вызывает инструменты этого сервера через https://www.n2j.ru/mcphub/mcp: hub_call_tool {"server":"ai-nothumansearch-search","tool":"…","arguments":{…}} Ключ не нужен, но сервер N2J ограничивает частоту анонимных вызовов.

https://nothumansearch.ai/mcp

Инструменты

14 схем · ≈ 3 729 условных токенов

search_agents

Search for websites, APIs, and services that AI agents can actually use. Results are ranked by agentic readiness score (0-100) based on llms.txt, OpenAPI specs, ai-plugin.json, structured APIs, and MCP server availability. Use this to discover payment APIs, job boards, data sources, or any web service your agent needs to call.

Показать схему аргументов
{
    "type": "object",
    "properties": {
        "limit": {
            "type": "integer",
            "maximum": 20,
            "minimum": 1,
            "description": "Max results (default 10, max 20)"
        },
        "query": {
            "type": "string",
            "description": "Keyword query (e.g. 'payment API', 'weather data', 'job board')"
        },
        "has_api": {
            "type": "boolean",
            "description": "Only return sites with a documented structured API"
        },
        "has_mcp": {
            "type": "boolean",
            "description": "Only return sites that expose an MCP server"
        },
        "category": {
            "enum": [
                "ai-tools",
                "developer",
                "data",
                "finance",
                "ecommerce",
                "jobs",
                "security",
                "health",
                "education",
                "communication",
                "productivity",
                "news"
            ],
            "type": "string",
            "description": "Filter by public category (ai-tools, developer, data, finance, ecommerce, jobs, security, health, education, communication, productivity, news). Audit-only buckets may appear in /api/v1/categories as other or spam, but are not promoted as discovery inventory."
        },
        "min_score": {
            "type": "integer",
            "maximum": 100,
            "minimum": 0,
            "description": "Minimum agentic readiness score 0-100 (higher = more agent-ready)"
        },
        "has_openapi": {
            "type": "boolean",
            "description": "Only return sites with a published OpenAPI / Swagger spec"
        },
        "has_llms_txt": {
            "type": "boolean",
            "description": "Only return sites that publish an llms.txt file (LLM-first site summary)"
        }
    }
}

get_site_details

Get the full agentic readiness report for a specific domain: score, category, all 7 signal checks (llms.txt, ai-plugin.json, OpenAPI, structured API, MCP server, robots.txt AI rules, Schema.org), plus any cached llms.txt content and OpenAPI summary. When an exact search id newly records this organic-result selection, the response also carries an optional record action interest opportunity for this domain. Selection alone is never interest and never contacts the provider.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "domain"
    ],
    "properties": {
        "domain": {
            "type": "string",
            "description": "Domain to look up (e.g. 'stripe.com'). Do not include scheme or path."
        },
        "search_id": {
            "type": "string",
            "description": "Optional receipt returned by a receipt-bearing NHS discovery tool. If this domain was returned, NHS records a detail selection and may return a separate, noncommercial action-interest opportunity requiring explicit current-principal attestation."
        }
    }
}

get_stats

Current Not Human Search index stats: total sites, average agentic score, top category, sites added in the last 7 days, count of sites exposing an MCP server, and count scoring a perfect 100/100.

Показать схему аргументов
{
    "type": "object",
    "properties": []
}

submit_site

Submit a URL for NHS to crawl and score. Use when you discover an agent-first tool, API, or service that isn't in the index yet. NHS will fetch the site, check its 7 agentic signals (llms.txt, ai-plugin.json, OpenAPI, structured API, MCP server, robots.txt AI rules, Schema.org), compute a score, and add it to the index. The site becomes searchable within a few seconds if the crawl succeeds.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "url"
    ],
    "properties": {
        "url": {
            "type": "string",
            "description": "Full URL to submit (include scheme, e.g. 'https://example.com'). Homepage is best — NHS will check /.well-known/ paths, /robots.txt, /llms.txt, etc. relative to the site root."
        }
    }
}

check_url

On-demand agentic-readiness check for any URL. Runs the NHS 7-signal crawler live (llms.txt, ai-plugin.json, OpenAPI, structured API, MCP server, robots.txt AI rules, Schema.org) and returns a score 0-100 with per-signal breakdown. Use before calling an unfamiliar API to confirm it's agent-usable. Re-runnable without the submissions-table side-effect of submit site — ideal for verify-before-use workflows.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "url"
    ],
    "properties": {
        "url": {
            "type": "string",
            "description": "Full URL or bare domain (e.g. 'stripe.com' or 'https://stripe.com'). Homepage works best — NHS probes the /.well-known/ paths, /robots.txt, /llms.txt relative to the site root."
        }
    }
}

verify_mcp

Actively probe any URL to check if it is a live, spec-compliant MCP server. Sends a JSON-RPC tools/list request and verifies a valid response. Use this before depending on a third-party MCP endpoint — manifests and documentation can claim MCP support without actually serving it. Returns {verified: true/false, endpoint, note}.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "url"
    ],
    "properties": {
        "url": {
            "type": "string",
            "description": "Full URL of the MCP endpoint to probe (include scheme, e.g. 'https://example.com/mcp')."
        }
    }
}

register_monitor

Register an email to get alerted when the indicated domain's agentic readiness score drops. Useful for agents tracking a dependency's agent-readiness health — e.g. an agent that relies on stripe.com's MCP surface wants to know the moment it regresses. Returns an unsubscribe URL. Multiple monitors per email allowed, one per domain.

Показать схему аргументов
{
    "type": "object",
    "required": [
        "email",
        "domain"
    ],
    "properties": {
        "email": {
            "type": "string",
            "description": "Email address to receive alert"
        },
        "domain": {
            "type": "string",
            "description": "Domain to monitor (no scheme, e.g. 'stripe.com')"
        }
    }
}

list_categories

List all categories in the Not Human Search index with site counts and average agentic scores. Use this to understand what kinds of agent-ready services exist before searching — counts are live, so the distribution shifts as the index grows.

Показать схему аргументов
{
    "type": "object",
    "properties": []
}

get_top_sites

Get the highest-scored agent-ready sites in the index, optionally filtered by category. Organic order is always readiness-score order. A supported category creates a query-free discovery receipt that can support separately disclosed provider-funded actions and explicit action interest; unfiltered browsing stays free and does not enter the Stage 1 demand cohort.

Показать схему аргументов
{
    "type": "object",
    "properties": {
        "limit": {
            "type": "integer",
            "maximum": 50,
            "minimum": 1,
            "description": "Max results (default 10, max 50)"
        },
        "category": {
            "enum": [
                "ai-tools",
                "developer",
                "data",
                "finance",
                "ecommerce",
                "jobs",
                "security",
                "health",
                "education",
                "communication",
                "productivity",
                "news"
            ],
            "type": "string",
            "description": "Filter by public category (ai-tools, developer, data, finance, ecommerce, jobs, security, health, education, communication, productivity, news). Audit-only buckets may appear in /api/v1/categories as other or spam, but are not promoted as discovery inventory. Omit for all categories."
        }
    }
}

recent_additions

List agent-ready sites newly added to the Not Human Search index, sorted newest first. A supported category creates a query-free discovery receipt that can support separately disclosed provider-funded actions and explicit action interest; unfiltered catalog watching stays free and does not enter the Stage 1 demand cohort.

Показать схему аргументов
{
    "type": "object",
    "properties": {
        "days": {
            "type": "integer",
            "maximum": 90,
            "minimum": 1,
            "description": "Look back window in days (default 7, max 90)"
        },
        "limit": {
            "type": "integer",
            "maximum": 50,
            "minimum": 1,
            "description": "Max results (default 10, max 50)"
        },
        "category": {
            "enum": [
                "ai-tools",
                "developer",
                "data",
                "finance",
                "ecommerce",
                "jobs",
                "security",
                "health",
                "education",
                "communication",
                "productivity",
                "news"
            ],
            "type": "string",
            "description": "Filter by public category (ai-tools, developer, data, finance, ecommerce, jobs, security, health, education, communication, productivity, news). Audit-only buckets may appear in /api/v1/categories as other or spam, but are not promoted as discovery inventory. Omit for all categories."
        }
    }
}

find_mcp_servers

List sites in the index that expose a live MCP server, ranked by agentic readiness. The result set carries a query-free discovery receipt and any eligible provider-funded actions appear separately without changing organic order. Pairs naturally with verify mcp for a probe-before-use workflow.

Показать схему аргументов
{
    "type": "object",
    "properties": {
        "limit": {
            "type": "integer",
            "maximum": 20,
            "minimum": 1,
            "description": "Max results (default 10, max 20)"
        },
        "query": {
            "type": "string",
            "description": "Optional keyword to narrow results (e.g. 'payments', 'jobs', 'weather')"
        },
        "category": {
            "enum": [
                "ai-tools",
                "developer",
                "data",
                "finance",
                "ecommerce",
                "jobs",
                "security",
                "health",
                "education",
                "communication",
                "productivity",
                "news"
            ],
            "type": "string",
            "description": "Filter by public category (ai-tools, developer, data, finance, ecommerce, jobs, security, health, education, communication, productivity, news). Audit-only buckets may appear in /api/v1/categories as other or spam, but are not promoted as discovery inventory. Omit for all categories."
        }
    }
}

record_action_interest

Record the caller's attestation that its human or company principal currently wants one controlled next step with a site returned organically by a receipt-bearing NHS discovery tool. This creates a private Stage 1 demand receipt that expires with the source discovery receipt, no later than 30 days after it. It does not contact the provider, create an action ticket or charge, change rank or score, or count as commercial proof. No query, contact data, free-form text, or agent/principal identity is accepted. Exact v1 wording: https://nothumansearch.ai/privacy action-interest-v1

Показать схему аргументов
{
    "type": "object",
    "required": [
        "search_id",
        "domain",
        "action_type",
        "caller_attests_principal_interest",
        "confirmation_version"
    ],
    "properties": {
        "domain": {
            "type": "string",
            "description": "Bare domain that appeared in the referenced organic results; no scheme or path."
        },
        "search_id": {
            "type": "string",
            "description": "Committed privacy-safe receipt returned by a receipt-bearing NHS discovery tool."
        },
        "action_type": {
            "enum": [
                "quote",
                "trial",
                "demo",
                "booking",
                "application",
                "signup",
                "purchase"
            ],
            "type": "string",
            "description": "The one next step the principal currently wants."
        },
        "confirmation_version": {
            "enum": [
                "nhs-action-interest-v1"
            ],
            "type": "string",
            "description": "https://nothumansearch.ai/privacy#action-interest-v1"
        },
        "caller_attests_principal_interest": {
            "type": "boolean",
            "const": true,
            "description": "Caller attests current principal interest under the exact published v1 wording; this is not authority to contact the provider."
        }
    },
    "additionalProperties": false
}

prepare_provider_action

Prepare a signed action ticket for a separately disclosed provider-funded offer returned beside a receipt-bearing NHS discovery result. This step never returns the provider action URL or records a handoff. It requires the discovery receipt and the caller's explicit ticket-authorization attestation. It accepts controlled constraints only—no name, email, contact detail, raw prompt, agent identity, or principal identity fields. Discovery and direct provider access remain free; preparing a ticket charges neither party. Exact v1 wording: https://nothumansearch.ai/privacy consent-v1

Показать схему аргументов
{
    "type": "object",
    "required": [
        "offer_id",
        "search_id",
        "demand_topic",
        "principal_consent",
        "consent_version"
    ],
    "properties": {
        "urgency": {
            "enum": [
                "unspecified",
                "now",
                "7_days",
                "30_days",
                "researching"
            ],
            "type": "string"
        },
        "offer_id": {
            "type": "string",
            "description": "Provider-funded offer ID returned separately beside a receipt-bearing NHS discovery result."
        },
        "search_id": {
            "type": "string",
            "description": "Discovery receipt proving the provider appeared organically."
        },
        "budget_band": {
            "enum": [
                "unspecified",
                "under_100",
                "100_499",
                "500_1999",
                "2000_plus"
            ],
            "type": "string"
        },
        "region_code": {
            "type": "string",
            "description": "Optional uppercase ISO country or country-region code."
        },
        "demand_topic": {
            "enum": [
                "payments",
                "commerce",
                "jobs",
                "data",
                "search",
                "weather",
                "maps",
                "email",
                "messaging",
                "image",
                "video",
                "audio",
                "documents",
                "security",
                "finance",
                "health",
                "education",
                "news",
                "analytics",
                "automation",
                "productivity",
                "identity",
                "storage",
                "ai-tools",
                "developer-tools",
                "other"
            ],
            "type": "string",
            "description": "One controlled topic already present on the referenced search receipt."
        },
        "consent_version": {
            "enum": [
                "nhs-principal-consent-v1"
            ],
            "type": "string",
            "description": "https://nothumansearch.ai/privacy#consent-v1"
        },
        "principal_consent": {
            "type": "boolean",
            "const": true,
            "description": "Caller attests that the human/company principal authorized this ticket preparation under the published versioned wording."
        },
        "requirement_flags": {
            "type": "array",
            "items": {
                "enum": [
                    "api_access",
                    "mcp",
                    "sandbox",
                    "self_serve",
                    "enterprise",
                    "compliance",
                    "multilingual",
                    "human_support"
                ],
                "type": "string"
            },
            "maxItems": 8,
            "uniqueItems": true
        }
    },
    "additionalProperties": false
}

handoff_provider_action

Present the exact ticket bearer returned by prepare provider action. NHS records one privacy-safe handoff receipt, then returns the attributed provider action URL. Optionally and separately, the principal may authorize the exact DNS-verified provider to resolve only the ticket's controlled topic, region, USD budget band, urgency, and allowlisted requirement flags. Declining that optional disclosure does not block the handoff. No query, contact detail, agent/principal identity, network address, referrer, or user-agent is disclosed. The handoff and resolver charge neither party; only the provide

Показать схему аргументов
{
    "type": "object",
    "required": [
        "ticket_id",
        "attribution_token",
        "principal_handoff_consent",
        "handoff_consent_version"
    ],
    "properties": {
        "ticket_id": {
            "type": "string",
            "description": "Action ticket ID returned by prepare_provider_action."
        },
        "attribution_token": {
            "type": "string",
            "description": "Exact bearer returned by prepare_provider_action; NHS does not store the raw token."
        },
        "handoff_consent_version": {
            "enum": [
                "nhs-provider-handoff-consent-v1"
            ],
            "type": "string",
            "description": "https://nothumansearch.ai/privacy#handoff-consent-v1"
        },
        "principal_handoff_consent": {
            "type": "boolean",
            "const": true,
            "description": "Caller attests the principal authorized the separate observed handoff under the exact published wording."
        },
        "controlled_intent_disclosure_consent_version": {
            "enum": [
                "nhs-provider-controlled-intent-disclosure-consent-v1"
            ],
            "type": "string",
            "description": "https://nothumansearch.ai/privacy#controlled-intent-disclosure-consent-v1; required only when the optional disclosure consent is true."
        },
        "principal_controlled_intent_disclosure_consent": {
            "type": "boolean",
            "description": "Optional separate authorization for the exact DNS-verified provider to resolve the bounded controlled-intent bundle after handoff. False or omitted does not block handoff."
        }
    },
    "additionalProperties": false
}