YouTube Insights

Provides transcripts, video metadata, and integrated insights for YouTube videos via MCP endpoints.
  • python

0

GitHub Stars

python

Language

4 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": {
    "tejas-borate-wai-youtube_insights_mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "C:\\Users\\YourUser\\Desktop\\Youtube-Video-Insights\\youtube_insights_mcp",
        "run",
        "python",
        "main.py"
      ],
      "env": {
        "PYTHONWARNINGS": "ignore"
      }
    }
  }
}

You set up and run an MCP server that fetches YouTube transcripts, metadata, and auto-generated insights, then query it from an MCP client to extract structured video information quickly and programmatically.

How to use

You access this YouTube Insights MCP Server from an MCP client. The server exposes three principal capabilities: extract full transcripts in multiple languages, fetch video metadata such as title and author, and generate comprehensive insights that combine transcript, metadata, and a summary. Use the available tools to request just what you need: transcripts, metadata, or the complete insights bundle.

How to install

Prerequisites you need before starting are Python 3.10 or newer and the MCP runtime environment. You also need the Python dependencies required by the server. Follow these steps to set everything up and run the server.

  1. Ensure Python 3.10+ is installed on your system.

  2. Prepare the MCP runtime dependencies by syncing or installing the MCP components as needed by your environment.

  3. Start the server using the runtime command shown here.

  4. Run the server script to begin listening for requests from your MCP client.

uv sync
python main.py

Configuration and notes

Configure the MCP client to connect to your YouTube Insights server using the following example configuration. This sets up a local stdio-based MCP server that executes the Python script to run the server.

{
  "mcpServers": {
    "youtube_insights": {
      "command": "uv",
      "args": [
        "--directory",
        "C:\\Users\\YourUser\\Projects\\Youtube-Video-Insights\\youtube_insights_mcp",
        "run",
        "python",
        "main.py"
      ]
    }
  }
}

Notes and capabilities

Supported URL formats include YouTube standard links, shortened links, embed links, shorts, and direct video IDs. The server is capable of returning structured results for transcripts, metadata, and the combined insights. If a transcript is disabled, unavailable, or the video is not accessible, the server responds with a clear error message in JSON.

Error handling and troubleshooting

If you encounter errors such as invalid URLs, unavailable transcripts, or network issues, check that the provided video ID or URL is correct and that the video permits transcript extraction. Ensure the Python environment has the necessary dependencies installed and that the MCP runtime is running with access to the main script.

Available tools

get_youtube_transcript

Fetches the full transcript for a YouTube video in the requested languages.

get_youtube_metadata

Retrieves metadata such as title, author, and thumbnail for a YouTube video.

get_youtube_insights

Provides a combined output including transcript, metadata, and a generated summary for a YouTube video.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational