AGENT SKILL

not-human-search-mcp

Search AI-ready websites, inspect indexed site details, verify MCP endpoints, and discover tools and APIs using the Not Human Search MCP server

License 许可
MIT
最近更新
2026-11-10
Stars
★ 1
Forks
0

01 前言 Front Matter

name
not-human-search-mcp
risk
safe
tags
[ "mcp", "search", "ai-discovery", "api-discovery", "mcp-verification", "agent-tools" ]
tools
[ "claude", "cursor", "gemini" ]
author
unitedideas
source
https://nothumansearch.ai
category
mcp
date_added
2026-04-16
description
Search AI-ready websites, inspect indexed site details, verify MCP endpoints, and discover tools and APIs using the Not Human Search MCP server
source_type
community

03 SKILL.md 正文

Not Human Search MCP

Overview

Not Human Search is a remote MCP server that lets AI agents search a curated index of 1,750+ AI-ready websites, inspect indexed site details, submit new sites for analysis, and verify live MCP endpoints via JSON-RPC probe. It is designed for AI agents that need to discover tools, APIs, and services at runtime without relying on hardcoded lists.

When to Use This Skill

  • Use when an AI agent needs to discover tools, APIs, or MCP servers for a specific task
  • Use when you want to check whether a website exposes machine-readable endpoints (llms.txt, OpenAPI, MCP)
  • Use when verifying that an MCP endpoint is actually responding to JSON-RPC
  • Use when building agent workflows that need to find and connect to external services dynamically

MCP Configuration

Add the Not Human Search MCP server to your client configuration. The endpoint uses streamable HTTP and requires no authentication.

Claude Desktop / Cursor / Windsurf

{
  "mcpServers": {
    "not-human-search": {
      "url": "https://nothumansearch.ai/mcp"
    }
  }
}

No API key or authentication is required.

Available Tools

search_agents

Search the index of 1,750+ AI-ready websites by keyword. Returns ranked results with scores, categories, and available endpoints.

search_agents({ query: "code review tools", limit: 10 })

get_site_details

Check a specific domain's AI-readiness score and available machine-readable endpoints.

get_site_details({ domain: "linear.app" })

get_stats

Get aggregate index statistics, including total indexed sites, categories, and endpoint coverage.

get_stats({})

submit_site

Submit a URL for crawling and AI-readiness analysis.

submit_site({ url: "https://example.com" })

verify_mcp

Verify whether a URL is a live MCP endpoint by sending a JSON-RPC probe and checking for a valid response.

verify_mcp({ url: "https://example.com/mcp" })

list_categories

List available discovery categories for narrowing searches.

list_categories({})

get_top_sites

Retrieve top-ranked indexed sites.

get_top_sites({ limit: 10 })

register_monitor

Register a domain monitor using a user-provided email address.

register_monitor({ domain: "example.com", email: "user@example.com" })

Examples

Example 1: Discover Code Review Tools

Use @not-human-search-mcp to find code review tools that expose MCP or API endpoints.

The agent will call search_agents({ query: "code review", limit: 10 }) and return ranked results with scores and endpoint details.

Example 2: Check if a Site is AI-Ready

Use @not-human-search-mcp to check the AI-readiness of linear.app.

The agent will call get_site_details({ domain: "linear.app" }) and return the site's score breakdown.

Example 3: Verify an MCP Endpoint

Use @not-human-search-mcp to verify that https://heliumtrades.com/mcp is a working MCP server.

The agent will call verify_mcp({ url: "https://heliumtrades.com/mcp" }) and confirm whether it responds to JSON-RPC.

Best Practices

  • Use search_agents for broad discovery, then get_site_details for detailed analysis of specific indexed results
  • Use verify_mcp to confirm an MCP endpoint is live before wiring it into an agent workflow
  • Use submit_site when a relevant site is absent from the index and the user wants it analyzed
  • Use register_monitor only with an email address the user explicitly provides for monitoring
  • Combine with other MCP skills to build dynamic tool-discovery pipelines

Limitations

  • The search index covers 1,750+ sites and is updated regularly, but may not include every site on the internet.
  • Scoring reflects machine-readable signals (llms.txt, OpenAPI, MCP, structured data) rather than content quality.
  • verify_mcp sends a JSON-RPC probe to the target URL; only use it on URLs you expect to be MCP endpoints.
  • register_monitor requires a user-provided email address and consent to receive monitoring notifications.

Related Skills

  • @mcp-builder - For building your own MCP servers
  • @ai-dev-jobs-mcp - Search AI/ML job listings via MCP

04 同仓库更多 Skills

YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

vercel-sandbox

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

slack

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

electron

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.

★ 1