Stripe Docs MCP server for AI agents
Let Claude, ChatGPT or your own agent read Stripe Docs: 2 typed functions through one MCP server. No Stripe Docs API key needed.
- Site
- stripe.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Stripe Docs
An MCP server for Stripe Docs 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/stripeEvery site
One MCP server for Stripe Docs 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
getDocReads one Stripe docs page by URL or path (docs.stripe.com/... or stripe.com/docs/...) and returns its title and full body as markdown, from the…Arguments
Name Type Required urlstringYes Returns
StripeDocinterface StripeDoc { url: string; title: string | null; markdown: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/stripe/getDocCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.stripe.getDoc("<url>");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.stripe.getDoc("<url>"))curl -X POST https://api.bowmark.ai/v1/sites/stripe/getDoc \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url":"<url>"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.stripe.getDoc("<url>");searchDocsSearches Stripe's public documentation (docs.stripe.com, formerly stripe.com/docs) for a topic and returns the best-matching guides.Arguments
Name Type Required argsstring | StripeSearchDocsArgsYes interface StripeSearchDocsArgs { query: string; limit?: number; }Returns
StripeDocHit[]interface StripeDocHit { title: string; url: string; markdownUrl: string; description: string | null; section: string | null; score: number; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/stripe/searchDocsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.stripe.searchDocs("refund");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.stripe.searchDocs("refund"))curl -X POST https://api.bowmark.ai/v1/sites/stripe/searchDocs \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":"refund"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.stripe.searchDocs("refund");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/stripe/<function> - OpenAPI
/v1/sites/stripe/openapi.json