MCP.Directory MCP server for AI agents
Let Claude, ChatGPT or your own agent read MCP.Directory: 1 typed function through one MCP server. No MCP.Directory API key needed.
- Site
- mcp.directory
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just MCP.Directory
An MCP server for MCP.Directory alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/mcp_directoryEvery site
One MCP server for MCP.Directory and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 1
searchSearches MCP.Directory's public catalogue of MCP servers by keyword, or browses its current listings.Arguments
Name Type Required querystring | { query?: string; limit?: number }No limitnumberNo Returns
McpDirectoryServer[]interface McpDirectoryServer { id: string; name: string; slug: string; description: string; classification: string | null; transportTypes: string[]; stars: number | null; githubStars: number | null; npmWeeklyDownloads: number | null; toolCount: number | null; publisher: { name: string; avatarUrl: string | null; verified: boolean } | null; url: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/mcp_directory/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.mcp_directory.search("weather");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.mcp_directory.search("weather"))curl -X POST https://api.bowmark.ai/v1/sites/mcp_directory/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query":"weather"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.mcp_directory.search("weather");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/mcp_directory/<function> - OpenAPI
/v1/sites/mcp_directory/openapi.json