LM Studio MCP server for AI agents

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

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

Connect

Just LM Studio

An MCP server for LM Studio 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/lmstudio
Every site

One MCP server for LM Studio 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
  • getDocFetches one lmstudio.ai/docs/... documentation page and returns its title and body content, instead of the caller having to already know the URL and…

    Arguments

    NameTypeRequired
    urlstringYes

    Returns lmstudioDoc

    interface lmstudioDoc {
      url: string;
      title: string;
      body: string;
    }

    HTTP endpoint

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

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.lmstudio.getDoc("<url>");
  • listDocPagesLists every documentation page lmstudio.ai publishes under /docs.

    Arguments

    None.

    Returns lmstudioDocPage[]

    interface lmstudioDocPage {
      url: string;
      slug: string;
    }

    HTTP endpoint

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

    Call it

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

Use it from code