Sponsored by Deepsite.site

📡 RSS MCP Server

Created By
akgoparaju6 months ago
Content

📡 RSS MCP Server

Status Python MCP

A modular Model Context Protocol (MCP) server for tracking, filtering, and surfacing PNT/GNSS news from custom RSS feeds with natural language interface via Claude Desktop.

✨ Features

  • 🔗 Native MCP Integration - Direct integration with Claude Desktop
  • 📰 RSS Feed Processing - Fetches and parses multiple RSS feeds
  • 🏷️ Tag-based Filtering - Content filtering using configurable tags
  • 💬 Natural Language Interface - AI-powered RSS management
  • 📊 State Management - Persistent read/unread article tracking
  • 🔍 Search Capabilities - Keyword and tag-based article search
  • 🛡️ Error Handling - Graceful fallbacks and error recovery

🚀 Quick Start

Prerequisites

  • Python 3.10+
  • Claude Desktop
  • Virtual environment (recommended)

Installation

# Clone the repository
cd rss-mcp-server

# Create and activate virtual environment
python3 -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install dependencies
pip install mcp feedparser pyyaml httpx

Configuration

  1. Create feeds.yaml (if not exists):
- url: https://insidegnss.com/feed/
  tags: [C-band, TrustPoint, GPSIA, LEO, PNT]
- url: https://spacenews.com/feed/
  tags: [LEO, spoofing, spectrum]
- url: https://www.gpsworld.com/feed/
  tags: [GNSS, spoof, jamming, M-code]
  1. Configure Claude Desktop:

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):

{
  "mcpServers": {
    "rss-mcp-server": {
      "command": "/path/to/your/project/.venv/bin/python",
      "args": ["/path/to/your/project/main.py"],
      "cwd": "/path/to/your/project"
    }
  }
}

⚠️ Replace paths with your actual project location

  1. Restart Claude Desktop completely (quit and reopen)

Testing

# Test server locally
python main.py
# Should output: "RSS MCP Server initialized successfully"

🤖 Usage

Once integrated with Claude Desktop, use natural language commands:

"Update my RSS feeds"
"Show me articles about GPS jamming"
"Search for LEO satellite articles"
"Mark the first 5 articles as read"
"Find articles about spoofing"
"Show me 10 recent unread articles"

📡 MCP Tools

ToolDescriptionParameters
update_rss_feedsFetch latest articles from all feedsNone
get_unread_articlesGet unread articleslimit (optional)
mark_articles_readMark articles as readarticle_ids (optional)
search_articlesSearch articles by keywordsquery, tags (optional)

📊 MCP Resources

Resource URIDescription
rss://feeds/unreadAll unread articles (JSON)
rss://feeds/allAll articles (JSON)

📁 Project Structure

rss-mcp-server/
├── main.py              # MCP server implementation
├── processor.py         # RSS feed processing logic
├── state.py            # State management for read/unread tracking
├── feeds.yaml          # Feed configuration (direct list format)
├── state.json          # Runtime state (auto-created)
├── requirements.txt    # Python dependencies
├── README.md          # This file
└── .venv/             # Virtual environment

⚙️ Configuration Details

feeds.yaml Format

✅ Correct format (direct list):

- url: https://example.com/feed/
  tags: [tag1, tag2, tag3]
- url: https://another.com/rss/
  tags: [tag4, tag5]

❌ Incorrect format (with wrapper):

feeds:  # Don't use this wrapper
  - url: https://example.com/feed/

Tags

Tags are used for:

  • Content filtering during search
  • Categorizing articles by topic
  • Enhancing search relevance

Example tags for PNT/GNSS content:

  • GPS, GNSS, PNT
  • jamming, spoofing, interference
  • LEO, MEO, satellites
  • military, defense, civilian
  • M-code, anti-jam, resilient

🔧 Troubleshooting

Common Issues

Server not appearing in Claude Desktop:

  • Verify claude_desktop_config.json syntax and paths
  • Ensure all paths are absolute
  • Restart Claude Desktop completely

Import errors:

pip install mcp feedparser pyyaml httpx

feeds.yaml format errors:

  • Use direct list format (start with -)
  • No feeds: wrapper needed
  • Ensure proper YAML syntax

File permission errors:

  • Ensure write permissions for state.json
  • Check directory permissions

Debug Steps

  1. Test locally: python main.py
  2. Check dependencies: pip list | grep -E "(mcp|feedparser|pyyaml|httpx)"
  3. Validate config: Check Claude Desktop logs
  4. Verify feeds: Test feed URLs in browser

🧪 Development

Running Tests

# Test RSS feed processing
python -c "from processor import RSSProcessor; import asyncio; asyncio.run(RSSProcessor().initialize())"

# Test state management
python -c "from state import StateManager; sm = StateManager(); print('State manager working')"

Adding New Feeds

  1. Add feed URL to feeds.yaml
  2. Configure appropriate tags
  3. Restart the MCP server
  4. Update feeds: "Update my RSS feeds"

Debugging

Enable debug output by modifying main.py:

import sys
print("Debug info", file=sys.stderr)

📈 Performance

  • Feed Updates: ~2-5 seconds for 3-5 feeds
  • Article Search: <1 second for typical queries
  • State Persistence: Automatic on read/unread changes
  • Memory Usage: ~10-20MB typical operation

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make changes with tests
  4. Submit a pull request

📄 License

MIT License - see LICENSE file for details

🆘 Support

  • Issues: Create GitHub issue with logs
  • Questions: Tag @anil.goparaju
  • Documentation: See Google Drive docs

🎯 Use Cases

Daily News Briefing:

"Update feeds and show me unread articles about GPS jamming and spoofing"

Research Assistance:

"Search for articles about LEO PNT systems published this week"

Competitive Intelligence:

"Find articles mentioning TrustPoint or military navigation systems"

Content Curation:

"Show me all unread articles, then mark the first 10 as read"

📊 Sample Output

When you search for "GPS jamming", you get structured results:

{
  "count": 3,
  "articles": [
    {
      "id": "251bc714...",
      "title": "U.S. Army Taking a Layered Approach to PNT",
      "link": "https://insidegnss.com/...",
      "published": "2025-06-03T16:58:20",
      "author": "Renee Knight",
      "feed_tags": ["C-band", "TrustPoint", "GPSIA", "LEO", "PNT"],
      "content": "...anti-jamming capabilities..."
    }
  ]
}

Last Updated: June 5, 2025
Status: ✅ Production Ready

Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
CursorThe AI Code Editor
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
DeepChatYour AI Partner on Desktop
Tavily Mcp
Amap Maps高德地图官方 MCP Server
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
WindsurfThe new purpose-built IDE to harness magic
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
ChatWiseThe second fastest AI chatbot™
Serper MCP ServerA Serper MCP Server
Playwright McpPlaywright MCP server
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code