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
関連サーバー
Bright Data
スポンサーDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
Web Fetch
Fetches and transforms web content, including JavaScript-rendered pages and media files, into various formats.
Playwright Server
Automate web browsers and perform web scraping tasks using the Playwright framework.
MCP Go Colly Crawler
A web crawling framework that integrates the Model Context Protocol (MCP) with the Colly web scraping library.
rssmcp
Fetches RSS feeds and returns entries as formatted text, with support for OPML configuration.
Selenix MCP
MCP server that bridges Claude Desktop (or any other local app supporting MCP) with Selenix for browser automation and testing. Enables creating, running, debugging, and managing browser automation tests through natural language.
Docs Fetch MCP Server
Fetch web page content with recursive exploration.
Riksdag & Regering MCP
MCP-server that provides LLMs with easy access to open data from the Swedish Government Offices and Parliament.
SubDownload
Public MCP wrapper for SubDownload.Fetch YouTube transcripts, search videos, browse channels and playlists — instant YouTube data for your AI workflow.
Apify
Extract data from any website with thousands of scrapers, crawlers, and automations
CompanyScope MCP
Company intelligence in one tool call — funding, tech stack, employees, competitors, news from public APIs