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
Похожие серверы
Bright Data
спонсорDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
Web Search
Performs web searches and extracts full page content from search results.
Decodo
Easy web data access. Simplified retrieval of information from websites and online sources.
Redbook Search & Comment Tool
An automated tool to search notes, analyze content, and post AI-generated comments on Xiaohongshu (Redbook) using Playwright.
RedNote MCP
Access and interact with content from Xiaohongshu (RedNote).
Mozilla Readability Parser
Extracts and transforms webpage content into clean, LLM-optimized Markdown using Mozilla's Readability algorithm.
MCP Browser Agent
A browser automation agent using the Model Context Protocol (MCP) to enable browser interactions.
MCP URL Format Converter
Fetches content from any URL and converts it to HTML, JSON, Markdown, or plain text.
getsonar-mcp
KYB due diligence, competitive intelligence, and strategic accounts research for AI agents. KYB covers corporate registries, sanctions screening (OFAC/UN/EU/UK), FCA Register lookup, directors, UBOs, and adverse media. CI covers pricing, hiring, product, sentiment, and corporate events. New accounts get 3 free trial calls. Pay-per-call after: $0.40 per /findings, $2.00 per /run with Claude analysis. Top up from $20 at getsonar.report.
Rendex Screenshot
Capture website screenshots as PNG/JPEG via AI agents. Full-page capture, dark mode, ad blocking, custom viewports. Edge-deployed on Cloudflare Workers, free tier included.
B2Proxy
1GB Free Trial, World's Leading Proxy Service Platform, Efficient Data Collection