Developer Tools

nothumansearch.ai

Indexes and evaluates websites for AI agent compatibility, providing agentic readiness scores and signal checks.

1 endpoint14 known toolsFirst detected June 5, 2026Last detected September 12, 2026

ENDPOINT 1

https://nothumansearch.ai/mcp

No auth detected

MCP server metadata

Name: nothumansearch
Version: 1.1.0

Capabilities

tools

Server instructions

Search engine for AI agents. Use search_agents to find agent-ready tools, APIs, and services ranked by agentic readiness score (0-100). Use get_site_details with the returned search_id to inspect one result and record selection only. If and only if the principal explicitly currently wants one supported next step with that selected domain, use the returned action_interest.call_contract to call record_action_interest; never infer interest from search, rank, selection, or provider availability. Recording interest contacts no provider and creates no ticket, charge, rank change, or commercial proof.

Known tools 14

search_agents

Search for websites, APIs, and services that AI agents can actually use.

Inferred read-only

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.

Inferred read-only

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.

Inferred read-only

submit_site

Submit a URL for NHS to crawl and score.

Inferred read-only

check_url

On-demand agentic-readiness check for any URL.

Inferred read-only

verify_mcp

Actively probe any URL to check if it is a live, spec-compliant MCP server.

Inferred read-only

register_monitor

Potential side effects

list_categories

List all categories in the Not Human Search index with site counts and average agentic scores.

Inferred read-only

get_top_sites

Get the highest-scored agent-ready sites in the index, optionally filtered by category.

Inferred read-only

recent_additions

List agent-ready sites newly added to the Not Human Search index, sorted newest first.

Inferred read-only

find_mcp_servers

List sites in the index that expose a live MCP server, ranked by agentic readiness.

Inferred read-only

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.

Inferred read-only

prepare_provider_action

Prepare a signed action ticket for a separately disclosed provider-funded offer returned beside a receipt-bearing NHS discovery result.

Inferred read-only

handoff_provider_action

Present the exact ticket bearer returned by prepare_provider_action.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.nothumansearch]
url = "https://nothumansearch.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "nothumansearch": {
      "type": "http",
      "url": "https://nothumansearch.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: nothumansearch
Remote MCP URL: https://nothumansearch.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

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

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "nothumansearch": {
      "type": "http",
      "url": "https://nothumansearch.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "nothumansearch",
  "transport": "streamable-http",
  "url": "https://nothumansearch.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for nothumansearch.ai was fetched 2026-07-27T23:59:12.009Z and is being refreshed.

Trust status Neutral

nothumansearch.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.