Vercel Docs MCP server for AI agents

Let Claude, ChatGPT or your own agent read Vercel Docs: 2 typed functions through one MCP server. No Vercel Docs API key needed.

Functions
2
Sign-in
Not needed
Works with
MCP, HTTP, Node, Python

Connect

Just Vercel Docs

An MCP server for Vercel 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/vercel
Every site

One MCP server for Vercel Docs and every other site Bowmark covers. Your agent looks up what it needs and calls it.

https://api.bowmark.ai/mcp
Set it up in your client

Both 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 Vercel documentation page by URL or /docs path and returns its first-party Markdown title, summary and body.

    Arguments

    NameTypeRequired
    urlstringYes

    Returns VercelDoc

    interface VercelDoc {
      url: string;
      title: string | null;
      summary: string | null;
      body: string;
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/vercel/getDoc

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.vercel.getDoc("/docs/getting-started-with-vercel");
  • listDocPagesLists Vercel's public documentation pages from its first-party Markdown sitemap, including title, URL and summary.

    Arguments

    None.

    Returns VercelDocLink[]

    interface VercelDocLink {
      title: string;
      url: string;
      summary: string | null;
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/vercel/listDocPages

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.vercel.listDocPages();

Use it from code