Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

mcp-youtube-transcript

MCP.Pizza Chef: jkawamoto

The mcp-youtube-transcript is an MCP server designed to retrieve transcripts for specified YouTube video URLs. It enables real-time access to video subtitles, facilitating text extraction from YouTube content for analysis, summarization, or integration into AI workflows. This server supports developers and applications needing structured video transcript data seamlessly.

Use This MCP server To

Extract transcripts from YouTube videos for text analysis Integrate YouTube video subtitles into AI-driven workflows Summarize YouTube video content using extracted transcripts Enable search and indexing of YouTube video speech content Convert YouTube video speech to text for accessibility tools Feed YouTube transcripts into language models for context Automate content review by analyzing YouTube video transcripts

README

YouTube Transcript MCP Server

Python Application GitHub License pre-commit Ruff smithery badge

This MCP server retrieves transcripts for given YouTube video URLs.

YouTube Transcript Server MCP server

Tools

This MCP server provides the following tools:

get_transcript

Fetches the transcript of a specified YouTube video.

Parameters
  • url (string): The full URL of the YouTube video. This field is required.
  • lang (string, optional): The desired language for the transcript. Defaults to en if not specified.

Installation

For Goose CLI

To enable the YouTube Transcript extension in Goose CLI, edit the configuration file ~/.config/goose/config.yaml to include the following entry:

extensions:
  youtube-transcript:
    name: Youtube Transcript
    cmd: uvx
    args: [--from, git+https://github.com/jkawamoto/mcp-youtube-transcript, mcp-youtube-transcript]
    enabled: true
    type: stdio

For Goose Desktop

Add a new extension with the following settings:

  • Type: Standard IO
  • ID: youtube-transcript
  • Name: Youtube Transcript
  • Description: Retrieve transcripts of YouTube videos
  • Command: uvx --from git+https://github.com/jkawamoto/mcp-youtube-transcript mcp-youtube-transcript

For more details on configuring MCP servers in Goose Desktop, refer to the documentation: Using Extensions - MCP Servers.

For Claude Desktop

To configure this server for Claude Desktop, edit the claude_desktop_config.json file with the following entry under mcpServers:

{
  "mcpServers": {
    "youtube-transcript": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/jkawamoto/mcp-youtube-transcript",
        "mcp-youtube-transcript"
      ]
    }
  }
}

After editing, restart the application. For more information, see: For Claude Desktop Users - Model Context Protocol.

Installing via Smithery

To install Youtube Transcript for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @jkawamoto/mcp-youtube-transcript --client claude

Using Proxy Servers

In environments where access to YouTube is restricted, you can use proxy servers.

When using Webshare, set the username and password for the Residential Proxy using either the environment variables WEBSHARE_PROXY_USERNAME and WEBSHARE_PROXY_PASSWORD, or the command line arguments --webshare-proxy-username and --webshare-proxy-password.

When using other proxy servers, set the proxy server URL using either the environment variables HTTP_PROXY or HTTPS_PROXY, or the command line arguments --http-proxy or --https-proxy.

For more details, please visit: Working around IP bans - YouTube Transcript API.

License

This application is licensed under the MIT License. See the LICENSE file for more details.

mcp-youtube-transcript FAQ

How do I provide a YouTube video URL to the server?
You supply the YouTube video URL as input to the MCP server's API endpoint to retrieve its transcript.
Does the server support transcripts for all YouTube videos?
The server retrieves transcripts only if the video has subtitles available, either auto-generated or uploaded.
In what format are transcripts returned?
Transcripts are typically returned in plain text or JSON format, structured by timestamps and text segments.
Can this server handle multiple video URLs in one request?
It depends on the implementation, but generally, the server processes one video URL per request for transcript retrieval.
Is authentication required to use this MCP server?
Authentication requirements depend on deployment; the server itself accesses public YouTube data without needing user credentials.
How does this server handle videos without transcripts?
If no transcript is available, the server returns an empty response or an error indicating transcript unavailability.
Can the transcripts be used with other LLM providers like Claude or Gemini?
Yes, transcripts retrieved can be fed into any LLM provider such as OpenAI, Claude, or Gemini for further processing.
What programming languages or frameworks is this server built with?
The server is implemented in Python, leveraging YouTube transcript APIs and MCP protocol standards.