Stack Overflow MCP server for AI agents
Let Claude, ChatGPT or your own agent read Stack Overflow: 2 typed functions through one MCP server. No Stack Overflow API key needed.
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Stack Overflow
An MCP server for Stack Overflow 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/stackoverflowEvery site
One MCP server for Stack Overflow 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
getQuestionReads one Stack Overflow question by id or url.Arguments
Name Type Required idnumber | stringYes Returns
StackOverflowQuestioninterface StackOverflowQuestionHit { questionId: number; title: string; link: string; tags: string[]; score: number | null; answerCount: number | null; isAnswered: boolean; acceptedAnswerId: number | null; viewCount: number | null; author: string | null; createdAt: string | null; } interface StackOverflowAnswer { answerId: number; score: number | null; isAccepted: boolean; author: string | null; createdAt: string | null; body: string; link: string; } interface StackOverflowQuestion extends StackOverflowQuestionHit { body: string; answers: StackOverflowAnswer[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/stackoverflow/getQuestionCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.stackoverflow.getQuestion(11227809);import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.stackoverflow.getQuestion(11227809))curl -X POST https://api.bowmark.ai/v1/sites/stackoverflow/getQuestion \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"id":11227809}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.stackoverflow.getQuestion(11227809);searchQuestionsSearches Stack Overflow questions by keyword and tag through the official Stack Exchange API, returning title, link, tags, score, answer count and…Arguments
Name Type Required argsstring | StackOverflowSearchArgsYes interface StackOverflowSearchArgs { query: string; tagged?: string; sort?: "relevance" | "votes" | "activity" | "creation"; limit?: number; }Returns
StackOverflowQuestionHit[]interface StackOverflowQuestionHit { questionId: number; title: string; link: string; tags: string[]; score: number | null; answerCount: number | null; isAnswered: boolean; acceptedAnswerId: number | null; viewCount: number | null; author: string | null; createdAt: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/stackoverflow/searchQuestionsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.stackoverflow.searchQuestions("branch prediction sorted array");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.stackoverflow.searchQuestions("branch prediction sorted array"))curl -X POST https://api.bowmark.ai/v1/sites/stackoverflow/searchQuestions \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":"branch prediction sorted array"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.stackoverflow.searchQuestions("branch prediction sorted array");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/stackoverflow/<function> - OpenAPI
/v1/sites/stackoverflow/openapi.json