convez.ai
MCP ServerBusca & PesquisaIntermediário
unitedideas

Not Human Search

unitedideas/nothumansearch

Buscador de sites agent-friendly com scoring automático de readiness

Ver no GitHub
BomPluginScore · de 0 a 100

Motor de busca especializado em sites preparados para agentes de IA, indexando e classificando por sinais de "agentic readiness" (llms.txt, OpenAPI, MCP, ai-plugin). Disponível como MCP server, REST API e interface web com mais de 8 mil sites indexados.

Instalação

$npx convez-ai unitedideas/nothumansearch

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
11
Forks
2
Acompanhando
0
Saúde
57%
Último commit
há 2 meses
Versão
—
Issues abertas
2
Contribuidores
5

Casos de uso

  • Descobrir APIs e serviços estruturados para integração com agentes Claude
  • Verificar preparação de um site para consumo por LLM agents
  • Encontrar MCP servers e endpoints prontos para automação
  • Construir catálogos de recursos machine-readable para aplicações autônomas

Veredito

Ferramenta prática e bem pensada para quem trabalha com agentes de IA. O scoring objetivo (llms.txt, OpenAPI, MCP) é claro, a integração via MCP é direta, e o índice de 8mil+ sites oferece cobertura real. Útil para discovery e validação de integrações.

README

A tradução para o português deste README ainda está na fila.

Not Human Search

NHS Agentic Readiness

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/stats for 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)

SignalPoints
llms.txt25
ai-plugin.json20
OpenAPI spec20
Structured API15
MCP server10
robots.txt5
Schema.org5

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

Ver o original no GitHub

Bom para

Relacionados