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
Servidores relacionados
Bright Data
patrocinadorDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
Oxylabs AI Studio
AI tools for web scraping, crawling, browser control, and web search via the Oxylabs AI Studio API.
MCP Webscan Server
Fetch, analyze, and extract information from web pages.
Puppeteer Real Browser
Enables powerful, detection-resistant browser automation for AI assistants using puppeteer-real-browser.
Weibo
Scrape Weibo user information, feeds, and perform searches.
TradingView Chart Image Scraper
Fetches TradingView chart images for a given ticker and interval.
Scrapfly
Scrapfly MCP Server gives AI agents a simple, unified way to scrape live web data with built-in anti-bot handling.
MCP YouTube Transcript Server
Retrieves transcripts from YouTube videos for content analysis and processing.
YouTube Data
Access YouTube video data and transcripts using the YouTube Data API.
scrape-do-mcp
MCP Server for Scrape.do - Web Scraping & Google Search with anti-bot bypass
transcriptor-mcp
An MCP server (stdio + HTTP/SSE) that fetches video transcripts/subtitles via yt-dlp, with pagination for large responses. Supports YouTube, Twitter/X, Instagram, TikTok, Twitch, Vimeo, Facebook, Bilibili, VK, Dailymotion. Whisper fallback — transcribes audio when subtitles are unavailable (local or OpenAI API). Works with Cursor and other MCP host