Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

MCP server for Hacker News — feeds, threads, users, and search via Firebase and Algolia APIs

README.md

<div align="center"> <h1>@cyanheads/hn-mcp-server</h1> <p><b>Browse Hacker News feeds, threads, and user profiles with full-text search via MCP. STDIO or Streamable HTTP.</b> <div>4 Tools</div> </p> </div>

<div align="center">

![Version](./CHANGELOG.md) ![License](./LICENSE) ![Docker](https://github.com/users/cyanheads/packages/container/package/hn-mcp-server) ![MCP SDK](https://modelcontextprotocol.io/) ![npm](https://www.npmjs.com/package/@cyanheads/hn-mcp-server) ![TypeScript](https://www.typescriptlang.org/) ![Bun](https://bun.sh/)

</div>

<div align="center">

![Install in Claude Desktop](https://github.com/cyanheads/hn-mcp-server/releases/latest/download/hn-mcp-server.mcpb) ![Install in Cursor](https://cursor.com/en/install-mcp?name=hn-mcp-server&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBjeWFuaGVhZHMvaG4tbWNwLXNlcnZlciJdfQ==) ![Install in VS Code](https://vscode.dev/redirect?url=vscode:mcp/install?%7B%22name%22%3A%22hn-mcp-server%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40cyanheads/hn-mcp-server%22%5D%7D)

![Framework](https://www.npmjs.com/package/@cyanheads/mcp-ts-core)

</div>

<div align="center">

Public Hosted Server: https://hn.caseyjhand.com/mcp

</div>

---

Tools

Four read-only tools for accessing Hacker News data:

| Tool Name | Description | |:----------|:------------| | hn_get_stories | Fetch stories from an HN feed (top, new, best, ask, show, jobs) with pagination. | | hn_get_thread | Get an item and its comment tree as a threaded discussion with depth/count controls. | | hn_get_user | Fetch a user profile with karma, about, and optionally a page of their submissions. | | hn_search_content | Search stories and comments via Algolia with type, author, date, and score filters. |

hn_get_stories

Fetch stories from any HN feed with pagination support.

  • Six feed types: top, new, best, ask, show, jobs
  • Configurable count (1–100, default 30) and offset for pagination
  • Returns enriched story objects with title, URL, score, author, comment count, and body text

---

hn_get_thread

Retrieve an item and its full comment tree via ranked breadth-first traversal.

  • Depth control (0–10, default 3) — depth 0 doubles as a single-item lookup
  • Comment limit (1–200, default 50) caps total comments across all levels
  • Breadth-first traversal preserves HN's ranking order
  • Flat comment list with depth/parentId for tree reconstruction

---

hn_get_user

Fetch a user profile with optional submission resolution.

  • Profile includes karma, creation date, and about text (HTML stripped)
  • Optionally resolves submissions into full items, up to 50 per page
  • submissionOffset pages through a long history; enrichment echoes the applied offset and the offset to request next
  • Submission resolution filters out dead/deleted items

---

hn_search_content

Full-text search via the Algolia HN Search API.

  • Filter by content type: story, comment, ask_hn, show_hn, front_page
  • Filter by author, date range (ISO 8601), and minimum points
  • Sort by relevance or date
  • Pagination with page/count controls
  • view: "compact" drops the two body-text fields (text, highlights.text), which otherwise repeat a long comment twice per hit — pass a hit id to hn_get_thread to read the body

Features

Built on @cyanheads/mcp-ts-core:

  • Declarative tool definitions — single file per tool, framework handles registration and validation
  • Unified error handling across all tools
  • Structured logging with request correlation
  • Runs locally (stdio/HTTP) from the same codebase

HN-specific:

  • Server-level instructions orientation forwarded to LLM clients on initialize — item types, ID reuse across tools, case-sensitive usernames, and field sparsity expectations
  • Concurrent batch fetching with configurable parallelism for item resolution
  • HTML entity decoding and tag stripping with code block and link preservation
  • No API keys required — HN APIs are public

Getting Started

Public Hosted Instance

A public instance is available at https://hn.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

{
  "mcpServers": {
    "hn-mcp-server": {
      "type": "streamable-http",
      "url": "https://hn.caseyjhand.com/mcp"
    }
  }
}

Self-Hosted / Local

Add to your MCP client configuration file:

{
  "mcpServers": {
    "hn-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/hn-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "hn-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/hn-mcp-server"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "hn-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MCP_TRANSPORT_TYPE=stdio",
        "ghcr.io/cyanheads/hn-mcp-server:latest"
      ]
    }
  }
}

Prerequisites

Installation

git clone https://github.com/cyanheads/hn-mcp-server.git
cd hn-mcp-server
bun install

Configuration

All configuration is via environment variables. No API keys required — HN APIs are public.

| Variable | Description | Default | |:---------|:------------|:--------| | HN_CONCURRENCY_LIMIT | Max concurrent HTTP requests for batch item fetches (integer, 1–50). | 10 | | MCP_TRANSPORT_TYPE | Transport: stdio or http. | stdio | | MCP_HTTP_PORT | HTTP server port. | 3010 | | MCP_HTTP_HOST | HTTP server host. | localhost | | MCP_LOG_LEVEL | Log level: debug, info, notice, warning, error. | info | | LOGS_DIR | Directory for log files (Node.js only). | <project-root>/logs |

Running the Server

Local Development

MCP_TRANSPORT_TYPE=stdio bun --watch src/index.ts   # Dev mode (stdio, auto-reload)
MCP_TRANSPORT_TYPE=http bun --watch src/index.ts    # Dev mode (HTTP, auto-reload)
bun run test                                         # Run test suite
bun run devcheck                                     # Lint + format + typecheck + audit

Production

bun run build
bun run start:stdio     # or start:http

Docker

docker build -t hn-mcp-server .
docker run -p 3010:3010 hn-mcp-server

Project Structure

| Directory | Purpose | |:----------|:--------| | src/index.ts | createApp() entry point. | | src/config/ | Server-specific env var parsing with Zod. | | src/services/hn/ | HN Firebase + Algolia API client and domain types. | | src/mcp-server/tools/definitions/ | Tool definitions (*.tool.ts). |

Development Guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

  • Handlers throw, framework catches — no try/catch in tool logic
  • Use ctx.log for request-scoped logging
  • All tools are read-only — no auth scopes required

Contributing

Issues and pull requests are welcome. Run checks before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Search servers.