Greenhouse MCP server for AI agents

Let Claude, ChatGPT or your own agent read Greenhouse: 1 typed function through one MCP server. No Greenhouse API key needed.

Functions
1
Sign-in
Not needed
Works with
MCP, HTTP, Node, Python

Connect

Just Greenhouse

An MCP server for Greenhouse 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/greenhouse
Every site

One MCP server for Greenhouse 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 1
  • listJobsLists every open job on one company's Greenhouse job board.

    Arguments

    NameTypeRequired
    companystringYes

    Returns GreenhouseBoard

    interface GreenhouseJob {
      id: string;              // Greenhouse's job id (gh_jid)
      title: string;
      location: string | null; // the board's own text, e.g. "Remote - US"
      department: string | null;
      url: string;             // the posting's public page
      firstPublished: string | null; // ISO
      updatedAt: string | null;      // ISO
      requisitionId: string | null;
    }
    
    interface GreenhouseBoard {
      board: string;           // the token, e.g. "stripe"
      boardUrl: string;
      companyName: string | null;
      total: number;
      jobs: GreenhouseJob[];
      warnings: string[];
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/greenhouse/listJobs

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.greenhouse.listJobs("stripe");

Use it from code