OpenAI Research & Blog MCP server for AI agents
Let Claude, ChatGPT or your own agent read OpenAI Research & Blog: 2 typed functions through one MCP server. No OpenAI Research & Blog API key needed.
- Site
- openai.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just OpenAI Research & Blog
An MCP server for OpenAI Research & Blog 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/openai_comEvery site
One MCP server for OpenAI Research & Blog 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
listPostsSearch OpenAI's research and blog posts by keyword or category (Research, Product, Safety, Company, etc.).Arguments
Name Type Required categorystringNo querystringNo limitnumberNo Returns
{ posts: OpenAiComPost[] }interface OpenAiComPost { title: string; url: string; slug: string; summary: string | null; category: string | null; published: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/openai_com/listPostsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.openai_com.listPosts({ limit: 5 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.openai_com.listPosts({"limit": 5}))curl -X POST https://api.bowmark.ai/v1/sites/openai_com/listPosts \ -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.openai_com.listPosts({ limit: 5 });readPostRead the complete text of any OpenAI research paper or blog post from openai.com by URL or slug.Arguments
Name Type Required urlstringNo slugstringNo Returns
OpenAiComArticleinterface OpenAiComArticle { title: string; url: string; category: string | null; description: string | null; text: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/openai_com/readPostCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.openai_com.readPost({ slug: "introducing-openai" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.openai_com.readPost({"slug": "introducing-openai"}))curl -X POST https://api.bowmark.ai/v1/sites/openai_com/readPost \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"slug":"introducing-openai"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.openai_com.readPost({ slug: "introducing-openai" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/openai_com/<function> - OpenAPI
/v1/sites/openai_com/openapi.json