Skip to main content
Glama
README.md
# YouTube MCP

A Model Context Protocol (MCP) server for YouTube integration.

## Prerequisites

### Install uv

**On Mac:**

```bash
brew install uv
```

**On Windows:**

```powershell
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
```

After installation on Windows, add uv to your PATH:

```cmd
set Path=C:\Users\nntra\.local\bin;%Path%
```

## Claude Desktop Integration

To use this MCP server with Claude Desktop, you need to add it to your Claude Desktop configuration.

1. Open your Claude Desktop configuration file:

   - **Mac**: `~/Library/Application Support/Claude/claude_desktop_config.json`
   - **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`

2. Add the following configuration to your `mcpServers` section (replace `/path/to/your/youtube-mcp` with the actual path to this project folder):

```json
{
  "mcpServers": {
    "youtube": {
      "command": "/Users/your-username/.local/bin/uv",
      "args": ["--directory", "/path/to/your/youtube-mcp", "run", "main.py"]
    }
  },
  "globalShortcut": ""
}
```

**Important:** Make sure to replace:

- `/path/to/your/youtube-mcp` with the actual path to where you cloned/downloaded this project
- `/Users/your-username/.local/bin/uv` with the correct path to your uv installation (on Windows this would typically be `C:\Users\your-username\.local\bin\uv.exe`)

3. Save the file and restart Claude Desktop

## Usage

Once configured, the YouTube MCP server will be available in Claude Desktop and you can use it to interact with YouTube data and functionality.

## Development

This project uses uv for dependency management. The dependencies are defined in `pyproject.toml` and the lockfile is `uv.lock`.

To run the server locally:

```bash
uv run main.py
```

TDQS

A3.8/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool has a clear, singular purpose focused on transcript extraction from YouTube videos.

Naming Consistency5/5

The single tool name follows a clear verb_noun pattern (get_youtube_transcript_tool), which would be consistent if there were more tools. There are no naming conflicts or inconsistencies to evaluate.

Tool Count2/5

A single tool is too few for a YouTube MCP server, which suggests a broader domain like video management, search, or analytics. This minimal toolset severely limits functionality and feels incomplete for the implied scope.

Completeness1/5

The toolset is severely incomplete for a YouTube server. It lacks basic operations such as searching videos, retrieving metadata, managing playlists, or handling comments. The single transcript tool covers only a narrow aspect of YouTube's capabilities.

Maintenance

ActivityInactive
ResponsivenessNo issues