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.
Oxylabs
Scrape websites with Oxylabs Web API, supporting dynamic rendering and parsing for structured data extraction.
Buienradar
Fetches precipitation data for a given latitude and longitude using Buienradar.
Browser MCP
A fast, lightweight MCP server that empowers LLMs with browser automation via Puppeteer’s structured accessibility data, featuring optional vision mode for complex visual understanding and flexible, cross-platform configuration.
WebScraping.AI
Interact with WebScraping.AI for web data extraction and scraping.
Playwright Server
A server providing Playwright tools for browser automation and web scraping.
Playwright MCP
Browser automation using Playwright, enabling LLMs to interact with web pages through structured accessibility snapshots.
Bilibili Comments
Fetch Bilibili video comments in bulk, including nested replies. Requires a Bilibili cookie for authentication.
Firecrawl
Extract web data with Firecrawl
Playwright Record MCP
Browser automation using Playwright with video recording. Enables LLMs to interact with web pages through structured accessibility snapshots.
Pip Server
Market Data