RSS Feed Manager MCP server

Enables AI to access and manage RSS feed content by parsing OPML files, fetching articles, and filtering content from subscribed sources
Back to servers
Provider
Buhe
Release date
Apr 01, 2025
Language
TypeScript
Package
Stats
726 downloads
8 stars

The MCP RSS server provides a way to interact with RSS feeds through the Model Context Protocol (MCP). It allows you to import RSS feed subscriptions, automatically fetch and update articles, and access RSS content through a structured API.

Installation Requirements

Prerequisites

  • Node.js (v14 or higher)
  • MySQL database

Setting Up MySQL

You can quickly set up a MySQL instance using Docker:

docker run -itd --name mysql-test -p 3306:3306 -e MYSQL_ROOT_PASSWORD=123456 mysql

Installing MCP RSS

MCP RSS uses stdio for communication. To install and run it:

npx mcp_rss

When using with Claude desktop, you can configure it in your settings:

{
  "key": "rss",
  "command": "npx",
  "args": [
    "mcp_rss"
  ],
  "env": {
    "OPML_FILE_PATH": "/path/to/your/feeds.opml"
  }
}

Configuration Options

Configure MCP RSS using the following environment variables:

Option Description Default Value
DB_HOST Database host localhost
DB_PORT Database port 3306
DB_USERNAME Database username root
DB_PASSWORD Database password 123456
DB_DATABASE Database name mcp_rss
OPML_FILE_PATH Path to your OPML file with RSS feeds "./feeds.opml"
RSS_UPDATE_INTERVAL Interval to fetch RSS updates (in minutes) 1

API Usage

Getting RSS Articles

Use the get_content method to retrieve articles from your subscribed RSS feeds:

Parameters:

Parameter Type Description Required
status string Filter by article status ("normal" or "favorite") No
source string Filter by source (feed title) No
limit number Maximum number of articles to return No (default: 10)

Example Response:

{
  "articles": [
    {
      "id": 1,
      "title": "Article Title",
      "content": "Article content...",
      "link": "https://example.com/article",
      "pubDate": "2023-01-01T12:00:00Z",
      "fetchDate": "2023-01-01T12:30:00Z",
      "status": "normal",
      "feedTitle": "Example Feed",
      "feedCategory": "Technology"
    }
  ],
  "success": true
}

Listing Available Sources

Use the get_sources method to retrieve all available RSS feed sources:

Parameters: None

Example Response:

{
  "sources": [
    {
      "id": 1,
      "title": "Example Feed",
      "category": "Technology"
    }
  ],
  "success": true
}

Managing Article Status

Use the set_tag method to mark articles as normal or favorite:

Parameters:

Parameter Type Description Required
status string Article status ("normal" or "favorite") Yes
articleId number ID of the article to update Yes

Example Response:

{
  "success": true,
  "message": "Article 1 status has been updated to favorite"
}

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later