Glassdoor MCP server for AI agents

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

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

Connect

Just Glassdoor

An MCP server for Glassdoor 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/glassdoor
Every site

One MCP server for Glassdoor 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
  • getEmployerReviewsAn employer's Glassdoor review summary.

    Arguments

    NameTypeRequired
    querystring | number | { url?: string; employerId?: string | number; name?: string }Yes

    Returns GlassdoorEmployerReviews | null

    interface GlassdoorEmployerReviews {
      employerId: string;           // Glassdoor's own numeric id, from the page's "-EI_IE<id>" URL segment
      name: string | null;          // null when the page's own structured data leaves it blank
      website: string | null;
      rating: number;               // e.g. 3.8
      ratingCount: number;
      bestRating: number;           // the top of Glassdoor's own scale, e.g. 5
      worstRating: number;          // the bottom of the scale, e.g. 1
      url: string;                  // the page's own canonical Overview URL
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/glassdoor/getEmployerReviews

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.glassdoor.getEmployerReviews("<query>");

Use it from code