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
관련 서버
Bright Data
스폰서Discover, extract, and interact with the web - one interface powering automated access across the public internet.
Scrapeless
Integrate real-time Scrapeless Google SERP(Google Search, Google Flight, Google Map, Google Jobs....) results into your LLM applications. This server enables dynamic context retrieval for AI workflows, chatbots, and research tools.
LinkRescue
MCP server that exposes LinkRescue's broken link scanning, monitoring, and fix suggestion capabilities to AI agents (Claude, Cursor, etc.).
Humanizer PRO
Humanizer PRO turn AI content into Human written content undetectable and bypass all AI detectors.
KonbiniAPI
KonbiniAPI gives AI agents direct access to social media data — profiles, posts, videos, comments, and search results.
Skyvern
MCP Server to let Claude / your AI control the browser
Web-curl
Fetch, extract, and process web and API content. Supports resource blocking, authentication, and Google Custom Search.
Anysite
Turn any website into an API
https://prowldata.dev/mcp
Real-world intelligence for AI agents via x402 micropayments. Prediction markets, economics, weather, narrative, and geopolitics.
Trends Hub
Aggregates trending topics from over 20 sources in real-time, with customizable fields and RSS feed support.
MCP Server Collector
Discovers and collects MCP servers from the internet.