agentsclimarketplace

Find mcp servers

Skill unitedideas/claude-skills-foundry/skills/find-mcp-servers

3 installable Claude Skills for agent tool discovery, AI/ML job search, and enterprise AI research citation.

Install
npx -y skills add unitedideas/claude-skills-foundry --skill find-mcp-servers

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use Not Human Search (nothumansearch.ai) to discover MCP servers and agent-friendly sites for a given task. Invoke when the user asks "what MCP server does X", "find me an MCP for Y", "is there an agent endpoint for Z", or otherwise needs to locate a Model Context Protocol server, agent-ready API, or LLM-compatible service.

SKILL.md

2.4 KB, 549 tokens by cl100k_base, as published. Nobody here has run it

Find MCP Servers via Not Human Search

Not Human Search (NHS) is an agent-native search engine that indexes 8,000+ sites scored on agentic readiness (llms.txt, OpenAPI, ai-plugin.json, MCP endpoints, structured APIs). Use it when the user needs to locate an MCP server or agent-compatible service.

How to call it

NHS exposes an MCP server at https://nothumansearch.ai/mcp over JSON-RPC. You can also hit the plain REST search at https://nothumansearch.ai/api/v1/search.

One-liner (REST, simplest)

curl -s "https://nothumansearch.ai/api/v1/search?q=$(python3 -c 'import urllib.parse,sys;print(urllib.parse.quote(sys.argv[1]))' "$ARGUMENTS")&per_page=5"

Expected shape:

{
  "query": "jira",
  "total": 12,
  "results": [
    {
      "url": "https://example.com",
      "title": "Example MCP for Jira",
      "score": 95,
      "summary": "MCP server exposing Jira issues, comments, sprints...",
      "has_mcp": true,
      "has_llms_txt": true
    }
  ]
}

MCP JSON-RPC call

curl -s -X POST https://nothumansearch.ai/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search","arguments":{"query":"'"$ARGUMENTS"'","limit":5}}}'

Available MCP tools: search, get_site, list_categories, get_top_sites, verify_mcp, check_llms_txt, check_openapi, monitor_register.

What to return to the user

  1. The top 3-5 results ranked by NHS agentic score (0-100).
  2. For each result: name, URL, score, a one-sentence summary of what the MCP/agent endpoint exposes, and which agent signals it has (MCP / llms.txt / OpenAPI).
  3. If nothing scores above 50, say so explicitly and suggest the user submit the target domain at https://nothumansearch.ai/submit so it gets crawled and scored.

Arguments

Pass the search query as $ARGUMENTS. Example: /find-mcp-servers stripe payments searches for MCP servers related to Stripe payments.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 327,069. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.