MCP Servers MCP server for AI agents
Let Claude, ChatGPT or your own agent read MCP Servers: 2 typed functions through one MCP server. No MCP Servers API key needed.
- Site
- mcpservers.org
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just MCP Servers
An MCP server for MCP Servers 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/mcpservers_orgEvery site
One MCP server for MCP Servers 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 2
searchSearches mcpservers.org's public MCP-server directory by keyword and returns listing rows.Arguments
Name Type Required args{ query: string }Yes Returns
McpServersOrgServer[]interface McpServersOrgServer { slug: string; name: string; category: string | null; description: string; stars: number | null; repository: string | null; url: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/mcpservers_org/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.mcpservers_org.search({ query: "weather" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.mcpservers_org.search({"query": "weather"}))curl -X POST https://api.bowmark.ai/v1/sites/mcpservers_org/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"weather"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.mcpservers_org.search({ query: "weather" });serverReads an MCP-server listing's public detail page by a slug returned from search().Arguments
Name Type Required args{ slug: string }Yes Returns
McpServersOrgServerinterface McpServersOrgServer { slug: string; name: string; category: string | null; description: string; stars: number | null; repository: string | null; url: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/mcpservers_org/serverCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.mcpservers_org.server({ slug: "isdaniel/mcp_weather_server" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.mcpservers_org.server({"slug": "isdaniel/mcp_weather_server"}))curl -X POST https://api.bowmark.ai/v1/sites/mcpservers_org/server \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"slug":"isdaniel/mcp_weather_server"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.mcpservers_org.server({ slug: "isdaniel/mcp_weather_server" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/mcpservers_org/<function> - OpenAPI
/v1/sites/mcpservers_org/openapi.json