OpenGathyr
An MCP server that enables managing and searching RSS feeds using tools like list, add, remove, get-feed, and search-feeds.
README
OpenGathyr
<img src="logo.svg" alt="OpenGathyr Logo" align="right" width="200" />
An open-source Model Context Protocol (MCP) server powered by RSS feeds.
What is OpenGathyr?
OpenGathyr transforms how you manage content feeds by providing a centralized hub that collects, processes, and distributes RSS/Atom feeds. Unlike traditional aggregators, OpenGathyr functions as a complete Model Context Protocol (MCP) server for your feed ecosystem.
Key Features
- MCP Tools Integration: Expose RSS feed functionality through standardized Model Context Protocol tools
- Automated Feed Refreshing: Configurable periodic fetching of RSS feeds to ensure fresh content
- Content Search: Search across all RSS feeds with a unified query interface
- Feed Management: Add, remove, and list RSS feeds dynamically
- Environment Configuration: Easy setup using environment variables for feed sources and settings
- Docker Ready: Containerized deployment support for both local and production environments
- Modular Architecture: Cleanly separated components for easier maintenance and extensibility
Getting Started
Prerequisites
- Node.js 22.x or higher
- npm 7.x or higher
- Docker (optional, for containerized deployment)
Installation
- Clone the repository:
git clone https://github.com/yourusername/opengathyr.git
cd opengathyr
- Install dependencies:
npm install
-
Create a
.envfile with your configuration (see Configuration section) -
Build the project:
npm run build
- Start the server:
npm start
For development with auto-reload:
npm run dev
Docker Deployment
To run the server in a Docker container:
# Build the Docker image
docker build -t opengathyr .
# Run the container
docker run -it opengathyr
Configuration
The server can be configured using environment variables:
MCP_SERVER_NAME: Name of the MCP serverMCP_SERVER_VERSION: Version of the MCP serverRSS_FEED_URL_1,RSS_FEED_URL_2, etc.: Individual RSS feed URLs (one URL per variable)RSS_REFRESH_INTERVAL: Refresh interval in milliseconds (default: 300000 = 5 minutes)RSS_MAX_ITEMS: Maximum number of items to keep per feed (default: 20)
Example .env file
MCP_SERVER_NAME=opengathyr
MCP_SERVER_VERSION=1.0.0
# RSS Feed URLs - one per line
RSS_FEED_URL_1=https://news.google.com/rss
RSS_FEED_URL_2=https://example.com/feed.xml
RSS_FEED_URL_3=https://another-site.org/rss
RSS_REFRESH_INTERVAL=300000
RSS_MAX_ITEMS=20
Available MCP Tools
get-feed
Retrieves the content from a specific feed.
Parameters:
feedName: Name of the feed to retrieve
search-feeds
Searches across all configured feeds for matching content.
Parameters:
query: Search term to look for in feed titles and content
list-feeds
Lists all currently configured feeds and their details.
Parameters: None
add-feed
Adds a new RSS feed to be monitored.
Parameters:
name: Identifier for the feedurl: URL of the RSS feedrefreshInterval(optional): Refresh interval in millisecondsmaxItems(optional): Maximum number of items to keep
remove-feed
Removes an RSS feed from monitoring.
Parameters:
feedName: Name of the feed to remove
Using with VS Code
GitHub Copilot Integration
To use OpenGathyr with GitHub Copilot in VS Code, you need to configure it as an MCP server in your Copilot settings.
Setup Steps
-
Build the MCP Server:
npm run build -
Configure Copilot MCP Settings:
Create or edit your Copilot configuration file. The location depends on your VS Code setup:
- Windows:
%APPDATA%\Code\User\globalStorage\github.copilot-chat\mcpServers.json - macOS:
~/Library/Application Support/Code/User/globalStorage/github.copilot-chat/mcpServers.json - Linux:
~/.config/Code/User/globalStorage/github.copilot-chat/mcpServers.json
Add your OpenGathyr server configuration:
{ "mcpServers": { "opengathyr": { "command": "node", "args": ["dist/index.js"], "cwd": "a:\\OpenGathyr", "env": { "MCP_SERVER_NAME": "opengathyr", "MCP_SERVER_VERSION": "1.0.0", "RSS_FEED_URL_1": "https://news.google.com/rss", "RSS_FEED_URL_2": "https://feeds.bbci.co.uk/news/rss.xml", "RSS_REFRESH_INTERVAL": "300000", "RSS_MAX_ITEMS": "20" } } } } - Windows:
-
Restart VS Code to apply the configuration changes.
-
Verify Connection:
Open GitHub Copilot Chat and try using the RSS feed tools:
@opengathyr list-feeds @opengathyr get-feed news @opengathyr search-feeds "technology"
Available Commands in Copilot Chat
Once configured, you can use these commands in GitHub Copilot Chat:
@opengathyr list-feeds- Lists all configured RSS feeds@opengathyr get-feed <feedName>- Gets content from a specific feed@opengathyr search-feeds <query>- Searches across all feeds@opengathyr add-feed <name> <url>- Adds a new RSS feed@opengathyr remove-feed <feedName>- Removes a feed
Example Usage
User: @opengathyr search-feeds "artificial intelligence"
Copilot: I'll search for AI-related content across your RSS feeds...
User: @opengathyr get-feed tech-news
Copilot: Here's the latest content from the tech-news feed...
Alternative: Direct MCP Client Usage
OpenGathyr includes a simple MCP client (src/client/mcp-client.ts) that can be used to interact with the MCP server for testing purposes.
Running the Client
Ensure the MCP server is not already running on the same port, then execute the client with:
npm run client
How It Works
The client:
- Spawns a new instance of the MCP server as a child process
- Sends a request to the
list-feedstool - Displays the formatted response
- Automatically terminates the server after receiving the response
Modifying the Client
You can easily modify the client to test other MCP tools:
// Change the request to use a different tool
const request = {
jsonrpc: '2.0',
id: 1,
method: 'tool',
params: {
name: 'get-feed', // Change to any of the available tools
params: {
feedName: 'example-feed' // Add required parameters for the tool
}
}
};
Available tools you can test:
list-feeds: Lists all configured feeds (no parameters needed)get-feed: Gets content from a specific feed (requiresfeedNameparameter)search-feeds: Searches across feeds (requiresqueryparameter)add-feed: Adds a new feed (requiresnameandurlparameters)remove-feed: Removes a feed (requiresfeedNameparameter)
Example for searching feeds:
const request = {
jsonrpc: '2.0',
id: 1,
method: 'tool',
params: {
name: 'search-feeds',
params: {
query: 'technology'
}
}
};
Use Cases
- AI Assistants: Integrate with LLM assistants via the Model Context Protocol to provide current news and information
- Content Aggregation: Centralize multiple RSS feeds into a single accessible interface
- News Monitoring: Track specific topics across multiple sources using the search functionality
- Headless CMS Integration: Feed dynamic content into websites and applications
- Research Tools: Collect and analyze content from multiple sources with a standardized API
Contributing
Contributions are welcome! Please see our Contributing Guide for details.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.