mcpField
R
RSS MCP Server

RSS MCP Server

Local
github.com/weekend-project-spaceProductivity5Updated 78w ago
Repository

About RSS MCP Server

RSS MCP Server is a FastMCP service for managing RSS feeds through the Fever API. It is for people who want to query feed content and manage item status from MCP clients such as Cursor.

Key features

  1. 01Retrieve RSS feeds and groups
  2. 02Query unread and saved items
  3. 03Filter items by feed or group
  4. 04Mark items read or saved

Use cases

  1. 01Review unread posts across RSS feeds
  2. 02Browse items by feed or group
  3. 03Manage read and saved status from a client

MCP support

The server exposes feed, group, and item retrieval and marking tools to MCP clients. It accesses RSS data through the Fever API.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

RSS MCP Server

中文文档

A FastMCP server implementation for RSS feed management using the Fever API.

Installation

  1. Clone the repository
  2. Install dependencies:
pip install -r requirements.txt

Configuration

  1. Copy .env.example to .env:
cp .env.example .env
  1. Edit .env and set your configuration values:
  • FEVER_API_URL: URL of your Fever API endpoint
  • FEVER_USERNAME: Your Fever API username
  • FEVER_PASSWORD: Your Fever API password
  • MCP_SERVER_NAME: Name for your MCP server instance
  1. Configure Cursor Integration:

Create or edit your Cursor MCP configuration file at ~/.cursor/mcp.json:

{
  "mcpServers": {
    "RssMcpServer": {
      "url": "http://127.0.0.1:8000/sse"
    }
  }
}

This configuration will allow Cursor to connect to your RSS MCP server running locally on port 8000.

Running the Server

Start the server using:

python main.py

API Tools

The server provides the following MCP tools:

Feed Management
  • get_feeds(): Retrieve all RSS feeds
  • get_groups(): Retrieve all feed groups
Item Operations
  • get_unread_items(max_items=10, max_id=9999999999, since_id="", feed_ids=None, group_ids=None): Get unread items
  • get_saved_items(max_items=10, max_id=9999999999): Get saved/favorited items
  • get_items(since_id=""): Get items since a specific ID
  • get_items_by_feed_ids(feed_ids, max_items=10): Get items from specific feeds
  • get_items_by_group_ids(group_ids, max_items=10): Get items from specific groups
  • mark_item(item_id, action): Mark items as read/saved/unsaved

Dependencies

  • starlette>=0.27.0
  • requests>=2.31.0
  • python-dotenv>=1.0.0
  • fastmcp>=0.1.0
  • uvicorn>=0.24.0

License

MIT License

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.