Youtube Summarizer

🚀 MCP Server

The MCP Server is built on top of all the APIs of the Youtube-Summarizer. All these APIs are exposed as tools via the MCP protocol and can be integrated into any AI application.

⚠️ Important Note

Currently, MCP only supports local connections, so remote use of these tools is not supported.

🚀 Quick Start

📦 Installation

Docker Setup

Build the Docker image:

docker build -t youtube-summarizer-mcp .

Run the MCP server using Docker:

docker run -i --rm youtube-summarizer-mcp

Using the Inspector

You can use the MCP Inspector to explore available tools and conduct tests:

./inspector.sh

Using on Claude Desktop

Add the following content to your claude_desktop_config.json:

{
  "mcpServers": {
    "youtube-summarizer": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "youtube-summarizer-mcp"
      ]
    }
  }
}

Now you can use the new MCP tools from server.py in Claude Desktop.

MCP Client Example (Without Claude Desktop)

Run the following commands to set up the MCP client locally:

Setup

./setup.sh

Run

./run.sh

It will run both the MCP server and the client and connect them to each other. The terminal will prompt the user to enter a natural language query, which will then be converted into an MCP tool call to answer the user's query.