mcpField
Y
yt-mcp-server

yt-mcp-server

Local
github.com/kdrSocial Media3Updated 78w ago
Repository

About yt-mcp-server

yt-mcp-server is an MCP server with utilities for YouTube URLs, video IDs, and thumbnails. It is intended for MCP clients that need to normalize links or construct video URLs.

Key features

  1. 01Normalize YouTube URLs
  2. 02Extract video IDs from URLs
  3. 03Build video watch URLs
  4. 04Build thumbnail URLs
  5. 05Set a playback start time

Use cases

  1. 01Convert varied YouTube links to canonical URLs
  2. 02Construct a watch link from a video ID
  3. 03Retrieve a video's thumbnail URL

MCP support

The MCP server exposes tools for normalizing YouTube URLs and generating watch and thumbnail URLs.

#yt-mcp-server#youtube-data#utility-functions

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "yt-mcp-server-kdr": {
      "command": "uvx",
      "args": [
        "git+https://github.com/kdr/yt-mcp-server.git"
      ]
    }
  }
}
Run commanduvx 'git+https://github.com/kdr/yt-mcp-server.git'

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypigit+https://github.com/kdr/yt-mcp-server.git

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

yt-mcp-server

MCP server with various utility functions for dealing with YouTube data. This server provides tools for working with YouTube URLs, video IDs, and thumbnails.

README image

📖 Resources

Prerequisites

  • Python 3.12 or higher
  • UV package manager

Setup

1. Install UV

If you haven't installed UV yet, you can install it using:

brew install uv
# alternatively curl -LsSf https://astral.sh/uv/install.sh | sh
2. Installation Methods
Method 1: Install from GitHub (Recommended)

This is the simplest way to install and run the server:

uvx --from git+https://github.com/kdr/yt-mcp-server.git server
Method 2: Local Development Setup

If you want to modify the code locally:

git clone https://github.com/kdr/yt-mcp-server.git
cd yt-mcp-server
uv venv
source .venv/bin/activate  # On Unix/macOS
# or
.venv\Scripts\activate  # On Windows
uv pip install -e .
3. Configure MCP Client

Add the following configuration to your MCP client settings:

{
    "mcpServers": {
        "yt-mcp-server": {
            "command": "uvx",
            "args": [
                "--from",
                "git+https://github.com/kdr/yt-mcp-server.git",
                "server"
            ]
        }
    }
}

For local development (Method 2), use this configuration instead:

{
    "mcpServers": {
        "yt-mcp-server": {
            "command": "uv",
            "args": [
                "--directory",
                "/ABSOLUTE/PATH/TO/PARENT/FOLDER/yt-mcp-server/yt_mcp_server",
                "run",
                "main.py"
            ]
        }
    }
}

Available Tools

The following tools are available to the LLM:

  • get_watch_url: Returns the YouTube watch URL for a given video ID, optionally starting at a specific time

    • Parameters:
      • video_id: The YouTube video ID
      • start_time: (Optional) The start time in seconds

  • get_thumbnail_url: Returns the thumbnail URL for a given YouTube video ID

    • Parameters:
      • video_id: The YouTube video ID

  • get_normalized_url: Normalizes various YouTube URL formats to the canonical watch URL and extracts the video ID

    • Parameters:
      • url: The YouTube URL to normalize

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.