Medium MCP server for AI agents
Let Claude, ChatGPT or your own agent read Medium: 3 typed functions through one MCP server. No Medium API key needed.
- Site
- medium.com
- Functions
- 3
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Medium
An MCP server for Medium 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/mediumEvery site
One MCP server for Medium 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
publicationPostsLists a Medium publication's latest public stories by publication slug or URL, with title, URL, publish date, tags, author and a text excerpt.Arguments
Name Type Required publicationstringYes Returns
MediumPost[]interface MediumPost { id: string | null; title: string; url: string; author: string | null; publishedAt: string | null; tags: string[]; excerpt: string | null }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/medium/publicationPostsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.medium.publicationPosts("better-programming");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.medium.publicationPosts("better-programming"))curl -X POST https://api.bowmark.ai/v1/sites/medium/publicationPosts \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"publication":"better-programming"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.medium.publicationPosts("better-programming");tagPostsLists the latest public Medium stories under one topic tag, with title, URL, publish date, tags, author and a text excerpt.Arguments
Name Type Required tagstringYes Returns
MediumPost[]interface MediumPost { id: string | null; title: string; url: string; author: string | null; publishedAt: string | null; tags: string[]; excerpt: string | null }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/medium/tagPostsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.medium.tagPosts("programming");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.medium.tagPosts("programming"))curl -X POST https://api.bowmark.ai/v1/sites/medium/tagPosts \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"tag":"programming"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.medium.tagPosts("programming");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/medium/<function> - OpenAPI
/v1/sites/medium/openapi.json