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
相關伺服器
Bright Data
贊助Discover, extract, and interact with the web - one interface powering automated access across the public internet.
Crew Risk
A crawler compliance risk assessment system via a simple API.
Yahoo Finance
Provides comprehensive financial data from Yahoo Finance, including historical prices, company info, financial statements, and market news.
infomate-mcp
MCP server that fetches and summarizes tech news from infomate.club/vas3k
AI Shopping Assistant
A conversational AI shopping assistant for web-based product discovery and decision-making.
Chrome Debug
Automate Chrome via its debugging port with session persistence. Requires Chrome to be started with remote debugging enabled.
scrape-do-mcp
MCP Server for Scrape.do - Web Scraping & Google Search with anti-bot bypass
Agentic Deep Researcher
A deep research agent powered by Crew AI and the LinkUp API.
Icypeas
Icypeas MCP allows agents to source leads in a gigantic +575M lead database, and enrich these leads with emails
powhttp-mcp
MCP server enabling agents to debug HTTP requests better
MCP Web Research Server
A server for web research that brings real-time information into AI models and researches any topic.