Install
$ agentstack add mcp-unitedideas-nothumansearch ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Not Human Search
[](https://nothumansearch.ai/site/nothumansearch.ai)
Search engine for AI agents. Indexes sites ranked by agentic readiness — llms.txt, OpenAPI, ai-plugin, MCP servers, and structured APIs.
🌐 Live site: nothumansearch.ai 🔌 MCP server: claude mcp add --transport http nothumansearch https://nothumansearch.ai/mcp 📊 Live score: nothumansearch.ai/score — check any URL 🛠 API: nothumansearch.ai/api/v1/search?q=
Why
LLM agents and autonomous systems can't "browse the web" efficiently the way humans do. They need machine-readable signals — llms.txt, OpenAPI schemas, MCP endpoints, ai-plugin manifests. NHS is the first search engine that explicitly ranks by how agent-friendly a site actually is, not by traditional SEO.
What's indexed
- 1,900+ agent-first sites scored across 7 agentic signals (see
/api/v1/statsfor current live count) - 500+ MCP servers with live JSON-RPC probe verification
- Agent-first filter — every indexed site has at least one strong agent signal (llms.txt, ai-plugin, OpenAPI, structured API, MCP server)
- Continuously refreshed via daily recrawl + weekly auto-discovery pipeline
Scoring (max 100)
| Signal | Points | |----------------|--------| | llms.txt | 25 | | ai-plugin.json | 20 | | OpenAPI spec | 20 | | Structured API | 15 | | MCP server | 10 | | robots.txt | 5 | | Schema.org | 5 |
How to use it
As an agent (MCP):
claude mcp add --transport http nothumansearch https://nothumansearch.ai/mcp
Tools include search_agents, find_mcp_servers, verify_mcp, check_url, recent_additions, list_categories, get_top_sites, get_site_details, get_stats, submit_site, register_monitor. Current full list: curl https://nothumansearch.ai/mcp -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'.
As a developer (HTTP API):
curl "https://nothumansearch.ai/api/v1/search?q=payments&limit=10"
As a human: just visit nothumansearch.ai.
Scoring your own site: nothumansearch.ai/score — paste a URL, get a breakdown + embed badge.
Stack
- Go 1.25 + Postgres on Fly.io (sjc)
- Single binary server + crawler
- MCP over streamable-http at
/mcp - IndexNow pings Bing/Yandex on every crawl cycle
Related
- aidevboard.com — AI Dev Jobs board (REST API + MCP; live listing count at
/api/v1/stats) - 8bitconcepts.com — Research papers on enterprise AI adoption
License
MIT
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: unitedideas
- Source: unitedideas/nothumansearch
- License: MIT
- Homepage: https://nothumansearch.ai
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.