RSS Reader is an RSS feed aggregation and article content extraction tool. It enables subscription to RSS feeds and retrieval of article lists, plus extracts full article content from URLs and formats it as clean Markdown. Key features of RSS Reader: - Fetch latest entries from any RSS feed URL with configurable limits (up to 100 entries) - Extract full article content from any article URL and convert to Markdown format - Retrieve structured feed metadata including title, link, publication date, and summary - Two transport modes: stdio (default) for local clients and HTTP streaming for containerized deployments - Compatible with MCP-capable clients like Claude Desktop and CherryStudio

RSS Reader MCP

An MCP (Model Context Protocol) server for RSS feed aggregation and article content extraction. You can use it to subscribe to RSS feeds and get article lists, or extract the full content of an article from a URL and format it as Markdown.

English | 中文

[](https://www.npmjs.com/package/rss-reader-mcp) [](LICENSE) [](https://github.com/kwp-lab/rss-reader-mcp/actions/workflows/publish.yml) [](https://smithery.ai/server/@kwp-lab/rss-reader-mcp)

🚀 Quick Start

You can use this MCP server in MCP-capable clients such as Claude Desktop and CherryStudio.

Claude Desktop

For Claude Desktop, add the following configuration under the "mcpServers" section in your claude_desktop_config.json file:

{
  "mcpServers": {
    "rss-reader": {
      "command": "npx",
      "args": [
        "-y",
        "rss-reader-mcp"
      ]
    }
  }
}

Usage Examples

> Can you fetch the latest 5 headlines from the BBC News RSS feed? > URL:

🔧 Tools Reference

fetch_feed_entries

Fetch RSS entries from a specified URL

Parameters:

Returns: A JSON object containing feed metadata and a list of entries (including title, link, publication date, and summary)

fetch_article_content

Extract article content from a URL and format it as Markdown

Parameters:

Returns: A JSON object containing the title, Markdown content, source URL, and timestamp

⚙️ Transport & Environment Variables

This server supports two transport modes:

Available environment variables:

How to switch transport modes:

Docker Deployment

You can also run this MCP server in a Docker container. First, build the image in the project root:

docker build -t rss-reader-mcp .

Using CherryStudio as an example, the following configuration shows how to run this server over HTTP:

{
  "mcpServers": {
    "rss-reader-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-p",
        "8081:8081",
        "-e",
        "PORT=8081",
        "rss-reader-mcp"
      ]
    }
  }
}

Some RSS Feeds for Testing