Index / MCP servers / Not Human Search

Not Human Search MCP server

Not Human Search is an MCP server with 14 tools an agent can call, among them check_url, find_mcp_servers, get_site_details. It answers at https://nothumansearch.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.

Status
Answering
Tools
14
Official
yes, served from nothumansearch.ai
Reliability
10 of 10 checks
Response time
400 ms
Transport
streamable HTTP
Last checked
17 October 2026

Search the agentic web. 1,900+ sites, 11 tools incl. check_url + verify_mcp for probe-before-use.

Description as the publisher wrote it.

The 14 tools Not Human Search offers

ToolWhat it does
check_urlOn-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 befo
Inputs: url
find_mcp_serversList 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 natur
Inputs: category, limit, query
get_site_detailsGet 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
Inputs: domain, search_id
get_statsCurrent 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.
get_top_sitesGet 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 provide
Inputs: category, limit
handoff_provider_actionPresent 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-verifie
Inputs: attribution_token, controlled_intent_disclosure_consent_version, handoff_consent_version, principal_controlled_intent_disclosure_consent, principal_handoff_consent, ticket_id
list_categoriesList 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
prepare_provider_actionPrepare 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
Inputs: budget_band, consent_version, demand_topic, offer_id, principal_consent, region_code
recent_additionsList 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; u
Inputs: category, days, limit
record_action_interestRecord 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 expire
Inputs: action_type, caller_attests_principal_interest, confirmation_version, domain, search_id
register_monitorRegister 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
Inputs: domain, email
search_agentsSearch 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 disco
Inputs: category, has_api, has_llms_txt, has_mcp, has_openapi, limit
submit_siteSubmit 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 se
Inputs: url
verify_mcpActively 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 M
Inputs: url

Add Not Human Search to your AI client

Every block below points at https://nothumansearch.ai/mcp. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http not-human-search https://nothumansearch.ai/mcp
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "not-human-search": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://nothumansearch.ai/mcp"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "not-human-search": {
      "url": "https://nothumansearch.ai/mcp"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "not-human-search": {
      "type": "http",
      "url": "https://nothumansearch.ai/mcp"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "not-human-search": {
      "url": "https://nothumansearch.ai/mcp"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "not-human-search": {
      "serverUrl": "https://nothumansearch.ai/mcp"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "not-human-search": {
      "url": "https://nothumansearch.ai/mcp"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: Not Human Search
version: 0.0.1
schema: v1
mcpServers:
  - name: Not Human Search
    type: streamable-http
    url: https://nothumansearch.ai/mcp
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "not-human-search": {
      "httpUrl": "https://nothumansearch.ai/mcp"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "not-human-search": {
      "type": "http",
      "url": "https://nothumansearch.ai/mcp"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "not-human-search": {
      "url": "https://nothumansearch.ai/mcp"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Fnothumansearch.ai%2Fmcp&type=streamable_http&id=not-human-search&name=Not%20Human%20Search

Is Not Human Search up right now?

It answered our last check on 17 October 2026 in 400 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to Not Human Search

Questions about Not Human Search

Is there an official Not Human Search MCP server?

Yes. It is published by nothumansearch.ai and served from nothumansearch.ai, the vendor's own domain: https://nothumansearch.ai/mcp.

How many tools does Not Human Search have?

14, as returned by the server's own tools/list on 8 September 2026: check_url, find_mcp_servers, get_site_details, get_stats, get_top_sites, handoff_provider_action, list_categories, prepare_provider_action, and 6 more.

Is Not Human Search down?

It answered our last check on 17 October 2026 in 400 ms. Over 10 checks since 4 September 2026 it answered 10.

How do I add Not Human Search to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://nothumansearch.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does Not Human Search need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: ai.nothumansearch. Endpoint host: nothumansearch.ai. ARD identifier: urn:air:ai.nothumansearch:mcp:search. First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.