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.json
file based onclaude_desktop_config.json.example
with 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
MCP Browser Agent
A browser automation agent using the Model Context Protocol (MCP) to enable browser interactions.
HotNews MCP Server
Provides real-time hot trending topics from major Chinese social platforms and news sites.
Buienradar
Fetches precipitation data for a given latitude and longitude using Buienradar.
MCP Rquest
An MCP server for making advanced HTTP requests with browser emulation, including PDF and HTML to Markdown conversion.
MCP Chrome Integration
Control the Chrome browser for web automation using an AI model. Requires the MCP Chrome extension.
Crypto News MCP Server
Fetches the latest cryptocurrency news and converts article content from HTML to Markdown.
Daft.ie MCP Server
Search and retrieve rental property details from Daft.ie via web scraping.
Kakuyomu MCP Server
An MCP server for the Kakuyomu novel posting site, enabling users to search for works, retrieve episode lists, and read content.
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.
Puppeteer MCP Server
Automate browser interactions using Puppeteer, controlling new or existing Chrome instances.