Mayo Clinic MCP server for AI agents
Let Claude, ChatGPT or your own agent read Mayo Clinic: 1 typed function through one MCP server. No Mayo Clinic API key needed.
- Site
- mayoclinic.org
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Mayo Clinic
An MCP server for Mayo Clinic 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/mayoclinicEvery site
One MCP server for Mayo Clinic 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 Mayo Clinic's diseases and conditions library for a health topic and returns the displayed title, summary and page URL.Arguments
Name Type Required args{ query: string }Yes Returns
MayoClinicSearchRow[]interface MayoClinicSearchRow { title: string; summary: string | null; url: string }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/mayoclinic/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.mayoclinic.search({ query: "diabetes" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.mayoclinic.search({"query": "diabetes"}))curl -X POST https://api.bowmark.ai/v1/sites/mayoclinic/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"diabetes"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.mayoclinic.search({ query: "diabetes" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/mayoclinic/<function> - OpenAPI
/v1/sites/mayoclinic/openapi.json