MCP RSS News Agent

A FastMCP-based RSS news aggregation and processing agent that can discover, fetch, and summarize content from various RSS feeds.

Features

• Discover RSS feeds from any website
• Fetch entries from RSS feeds
• Extract and format content from feed entries
• Extract and process web content from any URL
• Search news articles by keyword
• Generate summaries for news articles
• Get top news by category and country

Installation

1. Clone the repository
2. Install the required dependencies:

pip install -r requirements.txt

3. Create a .env file if you need environment variables (optional)

Usage

Start the MCP Server

python server.py

This will start the MCP server that exposes various RSS-related tools.

Available Tools

1. get_rss_feed_entries: Fetches entries from an RSS feed URL
2. discover_rss_feeds: Finds RSS feeds available on a website
3. download_feed_content: Downloads and processes the content of a feed entry
4. fetch_webpage: Extracts main content from any webpage URL using advanced techniques (NEW)
5. search_news_by_keyword: Searches news articles across multiple feeds using a keyword
6. create_news_summary: Creates summaries for news articles
7. get_top_news_from_category: Gets top news from specific categories and countries

Examples

Discover RSS Feeds on a Website

response = mcp.invoke("discover_rss_feeds", {"website_url": "https://www.theguardian.com"})
print(f"Found {response['feeds_count']} feeds")
for feed in response['feeds']:
    print(f"- {feed['title']}: {feed['url']}")

Get News Articles by Keyword

response = mcp.invoke("search_news_by_keyword", {
    "keyword": "climate change", 
    "max_results": 5
})
for article in response['results']:
    print(f"- {article['title']} ({article['source']})")
    print(f"  Link: {article['link']}")
    print()

Extract Content from Any Webpage

response = mcp.invoke("fetch_webpage", {
    "url": "https://example.com/article",
    "output_format": "markdown",
    "include_images": True
})
print(f"Title: {response['title']}")
print(f"Extraction method: {response['extracted_by']}")
print(f"Content preview: {response['content'][:200]}...")

Get Top News from a Category

response = mcp.invoke("get_top_news_from_category", {
    "category": "technology",
    "country": "us",
    "max_results": 3
})
for article in response['results']:
    print(f"- {article['title']} ({article['source']})")

Client Example

The project includes a command-line client (client_example.py) that provides easy access to all the MCP server tools:

# Get feed entries
python client_example.py feed https://www.theguardian.com/international/rss

# Search news by keyword
python client_example.py search "artificial intelligence"

# Extract content from a webpage with advanced extraction
python client_example.py webpage https://example.com/article --format markdown --images --save

# Get news by category
python client_example.py category technology --country us

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!