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
Related Servers
Bright Data
sponsorDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
YouTube Transcript Extractor
Extracts transcripts from public YouTube videos.
Apify
Extract data from any website with thousands of scrapers, crawlers, and automations
Canvas LMS
Links AI tools to Canvas school dashboards.
Oxylabs AI Studio
AI tools for web scraping, crawling, browser control, and web search via the Oxylabs AI Studio API.
Anysite
Turn any website into an API
Yahoo Finance
Interact with Yahoo Finance to get stock data, market news, and financial information using the yfinance Python library.
DataLayer
Give your AI agent access to 60M+ companies and 300M+ verified contacts. Enrich leads, find work emails, discover tech stacks, and identify buying intent — directly from Claude, Cursor, Windsurf, or any MCP-compatible AI agent.
Redfin MCP Server
Property search, price history, comparable sales, and neighborhood analysis
MCP Video Download URL Parser
Download watermark-free videos from platforms like Douyin and TikTok.
Sitemap MCP Server
A server for fetching, parsing, analyzing, and visualizing website sitemaps.