ai.nothumansearch/search

Official11 tools

Not Human Search

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

Search 4,100+ websites with URL verification and MCP probe tools for agents.

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.

Parameters (8)

categorystring
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_apiboolean
Only return sites with a documented structured API
has_llms_txtboolean
Only return sites that publish an llms.txt file (LLM-first site summary)
has_mcpboolean
Only return sites that expose an MCP server
has_openapiboolean
Only return sites with a published OpenAPI / Swagger spec
limitinteger
Max results (default 10, max 20)
min_scoreinteger
Minimum agentic readiness score 0-100 (higher = more agent-ready)
querystring
Keyword query (e.g. 'payment API', 'weather data', 'job board')

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.

Parameters (1)

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

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.

No parameters.

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.

Parameters (1)

urlstringrequired
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.

Parameters (1)

urlstringrequired
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}.

Parameters (1)

urlstringrequired
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.

Parameters (2)

domainstringrequired
Domain to monitor (no scheme, e.g. 'stripe.com')
emailstringrequired
Email address to receive alert

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.

No parameters.

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'.

Parameters (2)

categorystring
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.
limitinteger
Max results (default 10, max 50)

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.

Parameters (2)

daysinteger
Look back window in days (default 7, max 90)
limitinteger
Max results (default 10, max 50)

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.

Parameters (3)

categorystring
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.
limitinteger
Max results (default 10, max 20)
querystring
Optional keyword to narrow results (e.g. 'payments', 'jobs', 'weather')

Install

claude_desktop_config.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.