Google DeepMind MCP server for AI agents
Let Claude, ChatGPT or your own agent read Google DeepMind: 2 typed functions through one MCP server. No Google DeepMind API key needed.
- Site
- deepmind.google
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Google DeepMind
An MCP server for Google DeepMind 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/deepmindEvery site
One MCP server for Google DeepMind 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
listBlogPostsThe latest DeepMind blog/news posts from the site's own RSS feed.Arguments
Name Type Required limitnumberNo Returns
DeepMindBlogPost[]interface DeepMindBlogPost { title: string; url: string; summary: string | null; publishedAt: string | null; thumbnailUrl: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/deepmind/listBlogPostsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.deepmind.listBlogPosts({ limit: 5 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.deepmind.listBlogPosts({"limit": 5}))curl -X POST https://api.bowmark.ai/v1/sites/deepmind/listBlogPosts \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"limit":5}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.deepmind.listBlogPosts({ limit: 5 });listPublicationsOne page (30 rows, newest first) of DeepMind's research publications index at deepmind.google/research.Arguments
Name Type Required pagenumberNo querystringNo Returns
DeepMindPublicationsPageinterface DeepMindPublication { id: string; title: string; date: string; isoDate: string | null; url: string; } interface DeepMindPublicationsPage { page: number; total: number | null; publications: DeepMindPublication[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/deepmind/listPublicationsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.deepmind.listPublications({ page: 1 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.deepmind.listPublications({"page": 1}))curl -X POST https://api.bowmark.ai/v1/sites/deepmind/listPublications \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"page":1}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.deepmind.listPublications({ page: 1 });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/deepmind/<function> - OpenAPI
/v1/sites/deepmind/openapi.json