Skip to main content
Glama
YouTube Transcript MCP Server

YouTube Transcript MCP Server

YouTube Transcript MCP Server

A powerful Model Context Protocol (MCP) server that provides seamless access to YouTube video transcripts using the youtube-transcript-api library.

๐Ÿš€ Features

  • ๐Ÿ“ Get Full Transcripts - Fetch complete video transcripts in text or JSON format

  • ๐ŸŒ Multi-Language Support - Discover and fetch transcripts in different languages

  • ๐Ÿ” Smart Search - Search for specific text within video transcripts with context

  • ๐Ÿ“‹ Transcript Summaries - Get concise summaries of video content

  • ๐Ÿ”— URL Flexibility - Works with any YouTube URL format or direct video IDs

Related MCP server: YouTube Transcript MCP Server

๐Ÿ› ๏ธ MCP Tools Available

1. get_transcript

Fetch the complete transcript for a YouTube video.

Parameters:

  • video_url_or_id: YouTube video URL or video ID

  • languages: (Optional) List of language codes (e.g., ['en', 'es'])

  • format_type: (Optional) Output format - 'text' or 'json' (default: 'text')

2. get_available_languages

Get all available transcript languages for a video.

Parameters:

  • video_url_or_id: YouTube video URL or video ID

3. search_transcript

Search for specific text within a video's transcript.

Parameters:

  • video_url_or_id: YouTube video URL or video ID

  • query: Text to search for

  • languages: (Optional) List of language codes to search in

4. get_transcript_summary

Get a summary of the video's transcript.

Parameters:

  • video_url_or_id: YouTube video URL or video ID

  • max_length: (Optional) Maximum summary length in characters (default: 1000)

  • languages: (Optional) List of language codes to use

๐Ÿ“ฆ Installation

  1. Clone the repository:

git clone https://github.com/Ayaanisthebest/MCP-tool-for-YouTube-.git
cd MCP-tool-for-YouTube-
  1. Install dependencies:

pip install -e .
  1. Or install manually:

pip install youtube-transcript-api mcp[cli] fastmcp

โš™๏ธ MCP Configuration

Add to your MCP client configuration:

{
  "mcpServers": {
    "youtube-transcript": {
      "command": "python3",
      "args": ["-m", "youtube_transcript_mcp_server.server"]
    }
  }
}

Note: On macOS, use python3 instead of python. If you have a different Python setup, you can also use the full path:

{
  "mcpServers": {
    "youtube-transcript": {
      "command": "/opt/homebrew/bin/python3",
      "args": ["-m", "youtube_transcript_mcp_server.server"]
    }
  }
}

๐ŸŽฏ Usage Examples

Get a transcript:

get_transcript("https://www.youtube.com/watch?v=dQw4w9WgXcQ")

Search within a transcript:

search_transcript("dQw4w9WgXcQ", "never gonna give you up")

Get available languages:

get_available_languages("https://youtu.be/dQw4w9WgXcQ")

Get a summary:

get_transcript_summary("dQw4w9WgXcQ", max_length=500)

๐Ÿ”— Supported URL Formats

The server can extract video IDs from various YouTube URL formats:

  • https://www.youtube.com/watch?v=VIDEO_ID

  • https://youtu.be/VIDEO_ID

  • https://www.youtube.com/embed/VIDEO_ID

  • https://www.youtube.com/shorts/VIDEO_ID

  • Direct video ID: VIDEO_ID

๐Ÿงช Testing

Run the test script to verify everything works:

python3 test_server.py

๐Ÿ“‹ Dependencies

  • youtube-transcript-api>=0.6.2 - Core YouTube transcript functionality

  • mcp[cli]>=1.3.0 - Model Context Protocol support

  • fastmcp>=0.4.0 - FastMCP framework for easy MCP server development

๐Ÿ› Error Handling

The server includes comprehensive error handling for:

  • Invalid video URLs or IDs

  • Videos without transcripts

  • Network connectivity issues

  • Unsupported languages

  • Rate limiting

๐Ÿ“„ License

MIT License - see LICENSE file for details.

๐Ÿ‘จโ€๐Ÿ’ป About the Developer

Ayaan Ahmad - Full-Stack Developer & AI Enthusiast

I'm passionate about creating innovative tools that bridge the gap between AI and real-world applications. This YouTube Transcript MCP Server is part of my ongoing work to make AI more accessible and powerful through the Model Context Protocol ecosystem.

Connect with me:

  • GitHub: @Ayaanisthebest

  • Building the future of AI-powered tools, one MCP server at a time! ๐Ÿš€

๐Ÿค Contributing

Contributions are welcome! Please feel free to submit issues and pull requests.

๐Ÿ“ˆ Roadmap

  • Support for YouTube Shorts transcripts

  • Batch transcript processing

  • Transcript translation capabilities

  • Enhanced search with fuzzy matching

  • Transcript export to various formats


Made with โค๏ธ for the AI community

Available Tools

4 tools
get_available_languagesA

Get available transcript languages for a YouTube video.

Args: video_url_or_id: YouTube video URL or video ID ctx: MCP context for logging

Inputs: video_url_or_id (required). Returns: result

get_transcriptA

Fetch the transcript for a YouTube video.

Args: video_url_or_id: YouTube video URL or video ID languages: List of language codes to try (e.g., ['en', 'es']). If None, uses default. format_type: Output format - 'text' or 'json' ctx: MCP context for logging

Inputs: video_url_or_id (required), languages, format_type. Returns: result

get_transcript_summaryA

Get a summary of a YouTube video's transcript.

Args: video_url_or_id: YouTube video URL or video ID max_length: Maximum length of the summary in characters languages: List of language codes to use. If None, uses default. ctx: MCP context for logging

Inputs: video_url_or_id (required), languages, max_length. Returns: result

search_transcriptA

Search for specific text within a YouTube video's transcript.

Args: video_url_or_id: YouTube video URL or video ID query: Text to search for in the transcript languages: List of language codes to search in. If None, uses default. ctx: MCP context for logging

Inputs: query (required), video_url_or_id (required), languages. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelogโ€ฆ

    TDQS

    A4/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: fetching full transcripts, listing available languages, searching within a transcript, and summarizing a transcript. There is no overlap or ambiguity between them.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in snake_case (get_transcript, get_available_languages, search_transcript, get_transcript_summary). The verbs vary appropriately based on action, but the naming convention is uniform and predictable.

    Tool Count5/5

    With only 4 tools, the server is tightly scoped to transcript-related operations. Each tool serves a distinct and necessary function for the domain, making the count appropriate and well-balanced.

    Completeness5/5

    The tool set covers the core transcript workflow: retrieval, language discovery, searching, and summarization. There are no obvious dead ends or missing operations for a transcript-focused MCP server.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers