MCP RSS Crawler
Fetches and caches RSS feeds using a SQLite database for use with LLMs via the MCP protocol.
MCP-RSS-Crawler
An MCP (Message Chain Protocol) server that fetches RSS feeds and shares them with LLMs.
Features
- Fetching and caching of RSS feeds (SQLite database)
- MCP protocol implementation for seamless LLM integration
- Support for filtering feeds by category, source, or keywords
- Comprehensive API endpoints for feed management
- Add, update, and delete feeds
- Support for fetching articles from Firecrawl
Requirements
- Bun
- Firecrawl API key
- Claude Desktop or other MCP client
Setup as MCP Server
- Clone this repository
- Create a
claude_desktop_config.jsonfile based onclaude_desktop_config.json.examplewith your configuration
{
"mcpServers": {
"rss-crawler": {
"command": "/path/to/bun",
"args": ["run", "/path/to/mcp-rss-crawler/apps/mcp-server/src/mcp-cli.ts"],
"cwd": "/path/to/mcp-rss-crawler",
"env": {
"PORT": "5556",
"DB_DIR": "/path/to/mcp-rss-crawler",
"FIRECRAWL_API_KEY": "fc-<YOUR_FIRECRAWL_API_KEY>"
}
}
}
}
- Install dependencies:
bun install - Start Claude Desktop:
MCP Protocol
The server implements the Message Chain Protocol (MCP) which allows LLMs to access your latest RSS feeds. The MCP endpoint accepts POST requests with a JSON body containing a messages array and returns a response with the latest feed items.
Example request:
{
"messages": [
{
"role": "user",
"content": "What are the latest news from my RSS feeds?"
}
]
}
Example response:
{
"messages": [
{
"role": "assistant",
"content": "Here are the latest articles from your RSS feeds:",
"name": "rss-mcp"
},
{
"role": "tool",
"content": "[{\"title\":\"Article Title\",\"summary\":\"Article summary...\",\"published\":\"2025-03-16T04:30:00.000Z\",\"origin\":\"Feed Name\",\"link\":\"https://example.com/article\"}]",
"name": "rss-feeds"
}
]
}
Configuration Options
The server can be configured through environment variables or a .env file:
PORT- Server port (default: 5556)FIRECRAWL_API_KEY- Firecrawl API keyDB_DIR- Database directory (default:~/.mcp-rss-crawler)
Troubleshooting
- For connection issues, check your network settings and firewall configuration
- Logs are available in the console and can be used to diagnose problems
- For more detailed logging, set the
DEBUG=mcp-rss:*environment variable
Máy chủ liên quan
Bright Data
nhà tài trợDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
Fetch as Markdown MCP Server
Fetches web pages and converts them to clean markdown, focusing on main content extraction.
Fetcher MCP
Fetch and extract web content using a Playwright headless browser, with support for intelligent extraction and flexible output.
Hacker News
Fetches and parses stories from Hacker News, providing structured data for top, new, ask, show, and job posts.
Clawpage
Extract and structure any web page into clean JSON.
Internet-Names-MCP
Check availability of domain names, social media handles and subreddits
SABIS MCP Server
Access academic grades from the Sakarya University SABIS system via automated web scraping.
Web Scout
An MCP server for web search and content extraction using DuckDuckGo.
Conduit
Headless browser with SHA-256 hash-chained audit trails and Ed25519-signed proof bundles. MCP server for AI agents.
Cloudflare Playwright
Control a browser for web automation tasks like navigation, typing, clicking, and taking screenshots using Playwright on Cloudflare Workers.
Configurable Puppeteer MCP Server
A configurable MCP server for browser automation using Puppeteer.