MCP ExplorerExplorer

Mcp Rss Crawler

@mshkon 9 months ago
10 MIT
FreeCommunity
AI Systems
RSS Crawler MCP Server

Overview

What is Mcp Rss Crawler

mcp-rss-crawler is an MCP (Message Chain Protocol) server designed to fetch and manage RSS feeds, allowing integration with LLMs (Large Language Models).

Use cases

Use cases include creating a personalized news feed, integrating RSS feeds into chatbots, and developing applications that require up-to-date information from various sources.

How to use

To use mcp-rss-crawler, clone the repository, configure the ‘claude_desktop_config.json’ file, install dependencies using ‘bun install’, and start the server with Claude Desktop.

Key features

Key features include fetching and caching RSS feeds using an SQLite database, MCP protocol implementation for LLM integration, filtering feeds by category, source, or keywords, and comprehensive API endpoints for feed management.

Where to use

mcp-rss-crawler can be used in various fields such as news aggregation, content management systems, and applications requiring real-time updates from multiple RSS feeds.

Content

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

  1. Clone this repository
  2. Create a claude_desktop_config.json file based on claude_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>"
      }
    }
  }
}
  1. Install dependencies:
    bun install
    
  2. 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 key
  • DB_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

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers