Hacker News Reader MCP Server
Fetches Hacker News discussion threads and linked article content in LLM-optimized markdown format, enabling natural language analysis of HN posts and their conversations.
README
Hacker News Reader MCP Server
A Model Context Protocol (MCP) server that fetches Hacker News discussions and article content. Optimized for LLM consumption with compact, token-efficient formatting.
Features
✅ Fetch complete Hacker News discussion threads
✅ Scrape linked article content in markdown format
✅ LLM-optimized output (compact nested replies)
✅ Accepts both HN URLs and item IDs
✅ Handles edge cases (text posts, Ask HN, deleted comments)
✅ Powered by Firecrawl for robust article extraction
Installation
Using uvx from GitHub (Recommended)
uvx --from git+https://github.com/Malayke/hackernews-mcp.git hackernews-mcp
Using uv pip
uv pip install git+https://github.com/Malayke/hackernews-mcp.git
Using pip
pip install git+https://github.com/Malayke/hackernews-mcp.git
Usage
As an MCP Server
Add to your MCP settings configuration (e.g., in Claude Desktop or other MCP clients):
{
"mcpServers": {
"hackernews-mcp": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/Malayke/hackernews-mcp.git",
"hackernews-mcp"
],
"env": {
"FIRECRAWL_API_KEY": "your_api_key_here"
}
}
}
}
Or if you've installed it with pip/uv pip:
{
"mcpServers": {
"hackernews-mcp": {
"command": "hackernews-mcp",
"env": {
"FIRECRAWL_API_KEY": "your_api_key_here"
}
}
}
}
Environment Variables
Required:
FIRECRAWL_API_KEY- Your Firecrawl API key
Create a .env file:
FIRECRAWL_API_KEY=your_api_key_here
Available Tools
get_hn_content
Fetches Hacker News comments and the linked article content.
Input:
hn_url: HN URL or item ID- Full URL:
https://news.ycombinator.com/item?id=46130187 - Just ID:
46130187
- Full URL:
Output: Combined markdown with:
- Article Content - Scraped article in markdown format
- HN Discussion - Formatted comment threads with metadata
Example:
{
"hn_url": "https://news.ycombinator.com/item?id=46130187"
}
Output Format
The tool returns LLM-optimized content:
# ARTICLE CONTENT
[Article markdown content here...]
---
# HACKER NEWS DISCUSSION
STORY: Article Title
URL: https://example.com/article
AUTHOR: username | POINTS: 123 | TIME: 2 hours ago
TOTAL_COMMENTS: 45
COMMENT #1
COMMENT [author @ time] ID: 123456
Comment text here...
REPLY [author2 @ time] ID: 123457
Reply text here...
REPLY [author3 @ time] ID: 123458
Nested reply text...
COMMENT #2
...
Development
Local Setup
# Clone the repository
git clone https://github.com/Malayke/hackernews-mcp.git
cd hackernews-mcp
# Install dependencies with uv
uv sync
# Set up environment
echo "FIRECRAWL_API_KEY=your_api_key_here" > .env
# Run the server
uv run server.py
Testing
# Test the MCP server
uv run python test_mcp_server.py
Using in Development Mode
For local development with live changes:
{
"mcpServers": {
"hackernews-mcp": {
"command": "uv",
"args": [
"run",
"--directory",
"/path/to/hackernews-mcp",
"python",
"server.py"
],
"env": {
"FIRECRAWL_API_KEY": "your_api_key_here"
}
}
}
}
Requirements
- Python 3.11+
- Firecrawl API key (for article scraping)
Dependencies
mcp- Model Context Protocol SDKrequests- HTTP requestsbeautifulsoup4- HTML parsingfirecrawl-py- Article content extractionpython-dotenv- Environment variable management
License
MIT License - see LICENSE file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Links
Support
For issues, questions, or contributions, please visit the GitHub repository.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。