G2 MCP server for AI agents

Let Claude, ChatGPT or your own agent read G2: 3 typed functions through one MCP server. No G2 API key needed.

Site
g2.com
Functions
3
Sign-in
Not needed
Works with
MCP, HTTP, Node, Python

Connect

Just G2

An MCP server for G2 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/g2
Every site

One MCP server for G2 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 3
  • getProductReads one product's /products/<slug>/reviews page for its published aggregate rating, review count and category tags, off the page's own schema.org…

    Arguments

    NameTypeRequired
    args{ url: string } | stringYes

    Returns G2Product

    interface G2Product {
      name: string;
      url: string;
      categories: string[];
      rating: number | null;
      bestRating: number | null;
      reviewCount: number | null;
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/g2/getProduct

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.g2.getProduct({});
  • listReviewsThe 25 most recent reviews of one G2 product, off G2's own per-product review feed.

    Arguments

    NameTypeRequired
    args{ url?: string; slug?: string; stars?: number | number[]; limit?: number } | stringYes

    Returns G2ReviewList

    interface G2ReviewList {
      product: { slug: string; name: string; url: string };
      reviews: G2Review[];
    }
    
    interface G2Review {
      id: string;
      url: string;
      title: string;
      /** 0-5 in half-star steps */
      rating: number | null;
      /** ISO 8601 */
      publishedAt: string | null;
      reviewer: {
        /** "Verified User" when anonymous */
        name: string | null;
        role: string | null;
        companySize: string | null;
        industry: string | null;
      };
      likes: string | null;
      dislikes: string | null;
      problemsSolved: string | null;
      recommendations: string | null;
      /** every question/answer pair on the review, in G2's order */
      answers: { question: string; answer: string }[];
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/g2/listReviews

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.g2.listReviews({});

Use it from code