Youtube Summarizer

Provides MCP access to Youtube-Summarizer APIs for local AI integrations.

python

3

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

MCP Server exposes all APIs from the Youtube-Summarizer as MCP tools you can call from any MCP client. It runs locally and lets your AI applications discover and invoke those APIs through a unified MCP protocol, enabling seamless integration with your workflows while keeping everything self-contained on your machine.

How to use

You run the MCP server locally and connect an MCP client to it so you can ask for actions that the Youtube-Summarizer APIs provide. Start the server using the standard runtime command, then use your MCP client to issue natural-language requests. The client will translate your requests into tool calls and return results.

How to install

Prerequisites you need before installation: Docker must be installed and running on your system.

docker build -t youtube-summarizer-mcp .

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

Additional notes

If you want to explore the available tools and test them locally, you can use the Inspector to interact with the MCP server and try tool calls before integrating into an application. The Inspector provides a convenient way to validate how each API works within the MCP framework.

Notes on configuration and usage with MCP clients

To connect an MCP client to your locally running server, configure the client to reach the MCP endpoint provided by the Docker run. You can run the server in the background or foreground as shown above and reference it from your MCP client accordingly.

Inspector usage

./inspector.sh