VS Code Documentation MCP server for AI agents
Let Claude, ChatGPT or your own agent read VS Code Documentation: 2 typed functions through one MCP server. No VS Code Documentation API key needed.
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just VS Code Documentation
An MCP server for VS Code Documentation 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/vscodeEvery site
One MCP server for VS Code Documentation 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
getDocReturns one code.visualstudio.com documentation page's structured content by its URL.Arguments
Name Type Required urlstringYes Returns
VscodeDocinterface VscodeDoc { url: string; title: string; description: string; text: string; warnings: string[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/vscode/getDocCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.vscode.getDoc("<url>");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.vscode.getDoc("<url>"))curl -X POST https://api.bowmark.ai/v1/sites/vscode/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.vscode.getDoc("<url>");listDocPagesLists every doc page code.visualstudio.com publishes, parsed from the site's own /llms.txt index, each with its own url and one-line description…Arguments
None.
Returns
VscodeDocLink[]interface VscodeDocLink { title: string; url: string; description: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/vscode/listDocPagesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.vscode.listDocPages();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.vscode.listDocPages())curl -X POST https://api.bowmark.ai/v1/sites/vscode/listDocPages \ -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.vscode.listDocPages();
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/vscode/<function> - OpenAPI
/v1/sites/vscode/openapi.json