Hacker News 搜索工具

Hacker News 搜索与数据获取服务,提供全文搜索、热门/最新/Ask/Show/Job 故事获取以及评论读取能力,适用于 AI Agent、开发者及需要实时访问 Hacker News 社区内容的场景。

  • by pipeworx-io
  • JavaScript
  • 本地部署
  • 更新于
在 GitHub 查看 pipeworx-io/mcp-hackernews

使用说明

mcp-hackernews

Hacker News MCP — search and retrieve stories from Hacker News

Part of Pipeworx — an MCP gateway connecting AI agents to 1856+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

Tool Description
search_hn Full-text search Hacker News via Algolia. Pass query plus optional tags filter (story, comment, ask_hn, show_hn; default: story). Returns title, URL, score, author, comment count, and timestamp.
get_top_stories Fetch the current live top-ranked Hacker News stories from the Firebase API. Returns up to count stories (default 10) with title, URL, score, author, comment count, and Unix timestamp.
get_stories Fetch Hacker News stories of a given TYPE: top (default), new (newest), best, ask (Ask HN), show (Show HN), or job (jobs/hiring). PREFER for "newest HN stories", "top Ask HN posts", "Show HN", "HN job postings / who is hiring". Returns title, URL (or self-text for Ask/Show), score, author, comment count, and timestamp.
get_item Fetch a Hacker News story or comment by ID (e.g., "42153809"). Returns full text, score, author, timestamp, and child replies.
get_hn_comments Fetch the discussion (top-level comments, actual text) on a Hacker News story by its item ID. PREFER OVER WEB SEARCH for "what are people saying about ", "HN discussion / developer sentiment on X". get_item returns only comment IDs; this resolves them to text. Find a story ID via get_top_stories or search_hn. Returns each top comment author, text, time, and reply count.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "hackernews": {
      "url": "https://gateway.pipeworx.io/hackernews/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/hackernews/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1856+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/search_hn \
  -H 'Content-Type: application/json' \
  -d '{"query":"artificial intelligence"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/search_hn. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Run it from npm

@pipeworx/mcp-hackernews is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/hackernews/mcp endpoint shown above. It needs network access; there is no offline mode.

{
  "mcpServers": {
    "hackernews": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-hackernews"]
    }
  }
}

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Hackernews data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT