Product Hunt MCP server for AI agents

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

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

Connect

Just Product Hunt

An MCP server for Product Hunt 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/producthunt
Every site

One MCP server for Product Hunt 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
  • listLaunchesLists the latest product launches on Product Hunt (up to 50, newest first) from the site's own Atom feed.

    Arguments

    NameTypeRequired
    querystringNo
    limitnumberNo

    Returns producthuntLaunch[]

    interface producthuntLaunch {
      id: string;
      name: string;
      tagline: string;
      url: string;
      websiteUrl: string | null;
      hunter: string | null;
      publishedAt: string | null;
      updatedAt: string | null;
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/producthunt/listLaunches

    Call it

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

Use it from code