I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

mcp-rss-crawler
RSS Crawler MCP Server
3 years
Works with Finder
1
Github Watches
2
Github Forks
4
Github Stars
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.json
file based onclaude_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>"
}
}
}
}
- 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 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
相关推荐
Confidential guide on numerology and astrology, based of GG33 Public information
Converts Figma frames into front-end code for various mobile frameworks.
Advanced software engineer GPT that excels through nailing the basics.
Discover the most comprehensive and up-to-date collection of MCP servers in the market. This repository serves as a centralized hub, offering an extensive catalog of open-source and proprietary MCP servers, complete with features, documentation links, and contributors.
Micropython I2C-based manipulation of the MCP series GPIO expander, derived from Adafruit_MCP230xx
A unified API gateway for integrating multiple etherscan-like blockchain explorer APIs with Model Context Protocol (MCP) support for AI assistants.
Mirror ofhttps://github.com/suhail-ak-s/mcp-typesense-server
本项目是一个钉钉MCP(Message Connector Protocol)服务,提供了与钉钉企业应用交互的API接口。项目基于Go语言开发,支持员工信息查询和消息发送等功能。
Reviews

user_1peXqMF9
As an avid user of mcp and its related applications, I am thoroughly impressed by the mcp-rss-crawler developed by mshk. This tool efficiently retrieves and organizes RSS feeds, saving me the time and effort of manual browsing. The comprehensive capabilities of mcp-rss-crawler ensure that I stay updated with minimal hassle. Highly recommended for anyone looking to streamline their RSS feed consumption! Check it out at https://github.com/mshk/mcp-rss-crawler.