Not Human Search

Official11 toolsLive

by nothumansearch

Search the agentic web. 4,100+ sites, 11 tools incl. check_url + verify_mcp for probe-before-use.

ai.nothumansearch/search MCP Server

The ai.nothumansearch/search Model Context Protocol (MCP) server provides web search for an agentic web. It targets 4,100+ sites and exposes 11 tools, including check_url and verify_mcp for probe-before-use. The server is intended to support automated discovery and verification workflows.

🛠️ Key Features

Agentic web search
Coverage: 4,100+ sites
11 tools
Includes check_url and verify_mcp

🚀 Use Cases

Searching across a large set of web sources
Verifying MCP connectivity or endpoint readiness before use
Checking URLs before proceeding with downstream actions

⚡ Developer Benefits

Tooling for probe-before-use (check_url, verify_mcp)
Standardized MCP tooling count (11) for integration planning

⚠️ Limitations

Available details are limited to description-level metadata (no further tool behavior or configuration details provided)

Captured live from the server via tools/list.

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.

Parameters8

category	string	optional	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.
has_api	boolean	optional	Only return sites with a documented structured API
has_llms_txt	boolean	optional	Only return sites that publish an llms.txt file (LLM-first site summary)
has_mcp	boolean	optional	Only return sites that expose an MCP server
has_openapi	boolean	optional	Only return sites with a published OpenAPI / Swagger spec
limit	integer	optional	Max results (default 10, max 20)
min_score	integer	optional	Minimum agentic readiness score 0-100 (higher = more agent-ready)
query	string	optional	Keyword query (e.g. 'payment API', 'weather data', 'job board')

Raw schema

{
  "type": "object",
  "properties": {
    "category": {
      "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.",
      "enum": [
        "ai-tools",
        "developer",
        "data",
        "finance",
        "ecommerce",
        "jobs",
        "security",
        "health",
        "education",
        "communication",
        "productivity",
        "news"
      ],
      "type": "string"
    },
    "has_api": {
      "description": "Only return sites with a documented structured API",
      "type": "boolean"
    },
    "has_llms_txt": {
      "description": "Only return sites that publish an llms.txt file (LLM-first site summary)",
      "type": "boolean"
    },
    "has_mcp": {
      "description": "Only return sites that expose an MCP server",
      "type": "boolean"
    },
    "has_openapi": {
      "description": "Only return sites with a published OpenAPI / Swagger spec",
      "type": "boolean"
    },
    "limit": {
      "description": "Max results (default 10, max 20)",
      "maximum": 20,
      "minimum": 1,
      "type": "integer"
    },
    "min_score": {
      "description": "Minimum agentic readiness score 0-100 (higher = more agent-ready)",
      "maximum": 100,
      "minimum": 0,
      "type": "integer"
    },
    "query": {
      "description": "Keyword query (e.g. 'payment API', 'weather data', 'job board')",
      "type": "string"
    }
  }
}

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.

Parameters1

domain

string

required

Domain to look up (e.g. 'stripe.com'). Do not include scheme or path.

Raw schema

{
  "type": "object",
  "properties": {
    "domain": {
      "description": "Domain to look up (e.g. 'stripe.com'). Do not include scheme or path.",
      "type": "string"
    }
  },
  "required": [
    "domain"
  ]
}

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.

Parameters

No parameters.

Raw schema

{
  "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.

Parameters1

url

string

required

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.

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "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.",
      "type": "string"
    }
  },
  "required": [
    "url"
  ]
}

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.

Parameters1

url

string

required

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.

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "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.",
      "type": "string"
    }
  },
  "required": [
    "url"
  ]
}

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}.

Parameters1

url

string

required

Full URL of the MCP endpoint to probe (include scheme, e.g. 'https://example.com/mcp').

Raw schema

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

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.

Parameters2

domain	string	required	Domain to monitor (no scheme, e.g. 'stripe.com')
email	string	required	Email address to receive alert

Raw schema

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

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.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

get_top_sites

Get the highest-scored agent-ready sites in the index, optionally filtered by category. Returns sites ranked by agentic readiness score (100 = perfect agent support). Use this to discover the most agent-ready services overall or in a specific domain like 'finance' or 'developer'.

Parameters2

category	string	optional	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.
limit	integer	optional	Max results (default 10, max 50)

Raw schema

{
  "type": "object",
  "properties": {
    "category": {
      "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.",
      "type": "string"
    },
    "limit": {
      "description": "Max results (default 10, max 50)",
      "maximum": 50,
      "minimum": 1,
      "type": "integer"
    }
  }
}

recent_additions

List agent-ready sites newly added to the Not Human Search index, sorted newest first. Use this to discover what's just landed on the agentic web — new MCP servers, fresh llms.txt adopters, new OpenAPI publishers. Good for weekly agent digests or tracking ecosystem momentum.

Parameters2

days	integer	optional	Look back window in days (default 7, max 90)
limit	integer	optional	Max results (default 10, max 50)

Raw schema

{
  "type": "object",
  "properties": {
    "days": {
      "description": "Look back window in days (default 7, max 90)",
      "maximum": 90,
      "minimum": 1,
      "type": "integer"
    },
    "limit": {
      "description": "Max results (default 10, max 50)",
      "maximum": 50,
      "minimum": 1,
      "type": "integer"
    }
  }
}

find_mcp_servers

List sites in the index that expose a live MCP server, ranked by agentic readiness. Use this when your agent needs to discover callable MCP endpoints for a domain ('payments', 'jobs', 'search') or overall. Pairs naturally with verify_mcp for a probe-before-use workflow.

Parameters3

category	string	optional	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.
limit	integer	optional	Max results (default 10, max 20)
query	string	optional	Optional keyword to narrow results (e.g. 'payments', 'jobs', 'weather')

Raw schema

{
  "type": "object",
  "properties": {
    "category": {
      "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.",
      "type": "string"
    },
    "limit": {
      "description": "Max results (default 10, max 20)",
      "maximum": 20,
      "minimum": 1,
      "type": "integer"
    },
    "query": {
      "description": "Optional keyword to narrow results (e.g. 'payments', 'jobs', 'weather')",
      "type": "string"
    }
  }
}

Install

Tools (11)

search_agentsget_site_detailsget_statssubmit_sitecheck_urlverify_mcpregister_monitorlist_categories

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://nothumansearch.ai/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "search": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://nothumansearch.ai/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

ai.nothumansearch/search MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

search_agents

get_site_details

get_stats

submit_site

check_url

verify_mcp

register_monitor

list_categories

get_top_sites

recent_additions

find_mcp_servers

Install

Remote endpoint

Related servers