OpenAI MCP server for AI agents
Let Claude, ChatGPT or your own agent read OpenAI: 2 typed functions through one MCP server. No OpenAI API key needed.
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just OpenAI
An MCP server for OpenAI 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/openaiEvery site
One MCP server for OpenAI 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
helpArticleRetrieves the full text of a help article by its ID from OpenAI's documentation.Arguments
Name Type Required idstringYes Returns
stringHTTP endpoint
POST https://api.bowmark.ai/v1/sites/openai/helpArticleCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.openai.helpArticle({ id: "quickstart" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.openai.helpArticle({"id": "quickstart"}))curl -X POST https://api.bowmark.ai/v1/sites/openai/helpArticle \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"id":"quickstart"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.openai.helpArticle({ id: "quickstart" });plansReturns per-(plan, model) usage limits from learn.chatgpt.com/docs/pricing.Arguments
None.
Returns
openaiPlanLimit[]interface openaiPlanLimit { plan: string; model: string; usageRange: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/openai/plansCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.openai.plans();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.openai.plans())curl -X POST https://api.bowmark.ai/v1/sites/openai/plans \ -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.openai.plans();
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/openai/<function> - OpenAPI
/v1/sites/openai/openapi.json