MCP Collection MCP server for AI agents
Let Claude, ChatGPT or your own agent read MCP Collection: 3 typed functions through one MCP server. No MCP Collection API key needed.
- Functions
- 3
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just MCP Collection
An MCP server for MCP Collection 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/mcpcollection_comEvery site
One MCP server for MCP Collection 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 3
listLists MCP Collection's newest public server directory entries.Arguments
Name Type Required args{ limit?: number }No Returns
McpCollectionServer[]interface McpCollectionServer { slug: string; name: string; url: string; tagline: string | null; description: string; category: string; categoryLabel: string; repositoryUrl: string | null; homepageUrl: string | null; setup: string; endpointUrl: string | null; license: string | null; inBundle: boolean; featured: boolean; listedAt: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/mcpcollection_com/listCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.mcpcollection_com.list({});import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.mcpcollection_com.list({}))curl -X POST https://api.bowmark.ai/v1/sites/mcpcollection_com/list \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.mcpcollection_com.list({});searchSearches MCP Collection's public MCP-server directory by keyword.Arguments
Name Type Required args{ query: string; limit?: number }Yes Returns
McpCollectionServer[]interface McpCollectionServer { slug: string; name: string; url: string; tagline: string | null; description: string; category: string; categoryLabel: string; repositoryUrl: string | null; homepageUrl: string | null; setup: string; endpointUrl: string | null; license: string | null; inBundle: boolean; featured: boolean; listedAt: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/mcpcollection_com/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.mcpcollection_com.search({ query: "weather" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.mcpcollection_com.search({"query": "weather"}))curl -X POST https://api.bowmark.ai/v1/sites/mcpcollection_com/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.mcpcollection_com.search({ query: "weather" });serverReads one public MCP Collection server listing by its slug.Arguments
Name Type Required args{ slug: string }Yes Returns
McpCollectionServerinterface McpCollectionServer { slug: string; name: string; url: string; tagline: string | null; description: string; category: string; categoryLabel: string; repositoryUrl: string | null; homepageUrl: string | null; setup: string; endpointUrl: string | null; license: string | null; inBundle: boolean; featured: boolean; listedAt: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/mcpcollection_com/serverCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.mcpcollection_com.server({ slug: "github" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.mcpcollection_com.server({"slug": "github"}))curl -X POST https://api.bowmark.ai/v1/sites/mcpcollection_com/server \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"slug":"github"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.mcpcollection_com.server({ slug: "github" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/mcpcollection_com/<function> - OpenAPI
/v1/sites/mcpcollection_com/openapi.json