MCP Medium Accelerator

🚀 mcp-medium-accelerator

This MCP server enables LLMs like Claude Desktop. By inputting a URL such as "https://medium.com/tag/frontend/archive", it can extract links to the latest articles. It can create summaries, even in Italian, of the articles that interest the user. These summaries are saved in local storage for later querying.

🚀 Quick Start

This MCP server allows you to interact with Medium archives and manage article summaries. Here's a quick overview of how to get started.

✨ Features

• Extract links to the latest articles from Medium archive URLs.
• Create summaries of articles, optionally in Italian.
• Save article summaries locally for easy access.
• Manage saved summaries through various commands.

📦 Installation

Local Installation

1. Clone the repository:

git clone https://github.com/crtdaniele/mcp-medium-accelerator
cd mcp-medium-accelerator

2. Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate

3. Install the dependencies:

pip install -r requirements.txt

4. (Optional) Update the requirements.txt file after adding new libraries:

pip freeze > requirements.txt

Installation on Claude Desktop

mcp install main.py

Alternatively, manually configure the settings.json file (Claude Desktop > Settings > Advanced):

{
  "mcpServers": {
    "mcp-medium-accelerator": {
      "command": "/opt/homebrew/bin/uv",
      "args": [
        "run",
        "--with",
        "bs4",
        "--with",
        "httpx",
        "--with",
        "datetime",
        "--with",
        "tinydb",
        "--with",
        "mcp[cli]",
        "mcp",
        "run",
        "/your-local-path/main.py"
      ]
    }
  }
}

💻 Usage Examples

Starting the MCP Server

Development Mode with Hot Reload

mcp dev main.py

Normal Mode

mcp run main.py

Available Tools

• extract_article_links: Extracts article links from a Medium archive URL. Returns a list of article links.

• extract_article_text: Extracts the content of an article from a Medium URL. Returns the article content. Prompts the user to save the summary via save_summary.

• save_summary: Saves a summary of an article with title, URL, and tags. Returns a status message.

• list_summaries: Lists all saved summaries. Returns a list of summaries.

📄 License

This project is licensed under the MIT License. © 2025 Daniele Carta

Contributing

Pull requests are welcome!

Report bugs or request features by opening an issue.