APIDirectory MCP server for AI agents
Let Claude, ChatGPT or your own agent read APIDirectory: 2 typed functions through one MCP server. No APIDirectory API key needed.
- Site
- apidirectory.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just APIDirectory
An MCP server for APIDirectory 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/apidirectory_comEvery site
One MCP server for APIDirectory 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
listCategoriesLists APIDirectory's public API categories with category slugs, displayed names and current listing counts.Arguments
None.
Returns
ApiDirectoryCategory[]interface ApiDirectoryCategory { slug: string; name: string; listings: number; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/apidirectory_com/listCategoriesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.apidirectory_com.listCategories();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.apidirectory_com.listCategories())curl -X POST https://api.bowmark.ai/v1/sites/apidirectory_com/listCategories \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.apidirectory_com.listCategories();searchSearches APIDirectory's public registry by topic and returns each API's registry ID, slug, description, upstream URL, auth and spec labels…Arguments
Name Type Required querystring | { query: string }Yes Returns
ApiDirectoryApi[]interface ApiDirectoryApi { no: string; slug: string; name: string; description: string; url: string; auth: string; spec: string; pricingModel: string; status: string; categories: string[]; page: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/apidirectory_com/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.apidirectory_com.search("weather");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.apidirectory_com.search("weather"))curl -X POST https://api.bowmark.ai/v1/sites/apidirectory_com/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.apidirectory_com.search("weather");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/apidirectory_com/<function> - OpenAPI
/v1/sites/apidirectory_com/openapi.json