simply-feed-mcp
An MCP server for managing and querying RSS/news feeds, enabling real-time fetching, searching, and retrieval of feed items.
README
Simply Feed MCP Server
A Model Context Protocol (MCP) server for managing and querying RSS/news feeds. This server enables AI assistants to fetch, search, and retrieve information from RSS feeds in real-time.
MCP Tools
This server provides the following MCP tools:
get-recent-feed-items
Retrieve the most recent items from all configured news/RSS feeds within a specified time window.
recencyInMinutes(optional): Look back period in minutes (default: 120)limit(optional): Number of items to return (max: 50, default: 25)skip(optional): Number of items to skip for pagination
get-feed-items
Retrieve items from a specified news/RSS feed, ordered by recency (newest first), with pagination support.
feedId(required): The news/RSS feed ID from which to get itemslimit(optional): Number of items to return (max: 50, default: 25)skip(optional): Number of items to skip for pagination
search-feed-items
Search and retrieve items using natural language queries.
query(required): Description of the items to search forfeedId(optional): Filter results to a specific feedlimit(optional): Number of items to return (max: 50, default: 25)skip(optional): Number of items to skip for pagination
get-item-details
Get full details for a specific feed item.
feedId(required): The feed ID containing the itemid(required): The specific item ID
list-feeds
Retrieve a list of all configured RSS/news feeds with pagination support.
limit(optional): Number of feeds to return (max: 50, default: 10)skip(optional): Number of feeds to skip for pagination
Installation
Prerequisites
- Node.js 20+
- npm or yarn
From npm
Using npx (Recommended)
No installation required! Simply use npx to run the latest version:
Global Installation (Optional)
If you prefer to install globally:
npm install -g simply-feed-mcp
From Source
- Clone the repository:
git clone https://github.com/hmmroger/simply-feed-mcp.git
cd simply-feed-mcp
- Install dependencies:
npm install
- Build the project:
npm run build
Configuration
Feed Configuration
The feed configuration is used by the worker to fetch and update feeds.
Create a feeds.json file (or any custom filename) and specify its location using --config_file with your RSS feeds:
[
{
"feedUrl": "https://www.technologyreview.com/feed/"
}
]
Environment Variables
Configure the server using these environment variables:
| Variable | Description | Default | MCP/Worker |
|---|---|---|---|
SIMPLY_FEED_CONFIG_FILE_NAME |
Custom feeds config file name | feeds.json |
Worker |
SIMPLY_FEED_CONFIG_BLOB_NAME |
Load config from Azure Blob (format: container/blob) |
- | Worker |
SIMPLY_FEED_STORAGE_CONNECTION_STRING |
Azure Storage connection string | - | Both |
SIMPLY_FEED_STORAGE_FILE_FOLDER |
Local storage folder for feed data | - | Both |
SIMPLY_FEED_LLM_API_KEY |
API key for LLM integration | - | Both |
SIMPLY_FEED_LLM_BASE_URL |
Base URL for LLM API | https://generativelanguage.googleapis.com/v1beta/openai |
Both |
SIMPLY_FEED_LLM_MODEL |
LLM model to use | gemini-2.5-flash-lite |
Both |
SIMPLY_FEED_ITEMS_RETENTION_DAYS |
Days to retain feed items | - | Worker |
Usage
[!NOTE] You must have one instance of simply-feed-mcp running as a
workerto fetch and update feeds, otherwise the MCP server will not see any feeds.
Required Environment Variables
SIMPLY_FEED_LLM_API_KEY is required.
Background Worker
Run the background worker to continuously fetch and update feeds:
# Run continuously (default: refresh every 15 minutes)
npx simply-feed-mcp --worker
# Run once and exit
npx simply-feed-mcp --worker --run_once
# Custom refresh interval (in seconds)
npx simply-feed-mcp --worker --refresh_interval 600
# Use custom config file and path
npx simply-feed-mcp --worker --config_file /custom/path/my-feeds.json
# Use Azure Blob config
npx simply-feed-mcp --worker --config_blob_name container/feeds.json
MCP Server
Ensure you specify the same values for environment variables that were used in the worker.
Integration
Claude Desktop
Add to your Claude Desktop MCP configuration:
{
"mcpServers": {
"simply-feed-mcp": {
"command": "npx",
"args": [
"-y",
"simply-feed-mcp"
],
"env": {
"SIMPLY_FEED_LLM_API_KEY": "<API KEY>"
}
}
}
}
License
MIT License - see LICENSE file for details.
Support
- GitHub Issues: Report bugs or request features
- Repository: https://github.com/hmmroger/simply-feed-mcp
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.