Skip to main content
Glama

kzmshx-youtube-mcp

An MCP server for extracting YouTube video transcripts and metadata.

Configuration

{
  "mcpServers": {
    "youtube": {
      "command": "uvx",
      "args": ["kzmshx-youtube-mcp"]
    }
  }
}

Related MCP server: ytt-mcp

Installation (Optional)

If you prefer to install globally:

pip install kzmshx-youtube-mcp
# or
uv tool install kzmshx-youtube-mcp

Tools

get_transcript

Get transcript text from a YouTube video.

Parameter

Type

Description

url

string

YouTube URL or video ID

language

string

Language code (default: auto)

with_timestamps

bool

Include timestamps (default: false)

Example:

// Input
{ "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ" }

// Output
{
  "video_id": "dQw4w9WgXcQ",
  "language": "en",
  "transcript": "We're no strangers to love\nYou know the rules and so do I..."
}

get_video_info

Get metadata from a YouTube video.

Parameter

Type

Description

url

string

YouTube URL or video ID

Example:

// Input
{ "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ" }

// Output
{
  "id": "dQw4w9WgXcQ",
  "title": "Rick Astley - Never Gonna Give You Up",
  "description": "...",
  "duration": 213,
  "channel": "Rick Astley",
  "upload_date": "2009-10-25",
  "view_count": 1500000000,
  "available_languages": ["en", "ja", "es", "fr"]
}

License

MIT

Available Tools

2 tools
get_transcriptGet TranscriptC

Get transcript text from a YouTube video.

Inputs: url (required), language, with_timestamps. Returns: object

get_video_infoGet Video InfoC

Get metadata from a YouTube video.

Inputs: url (required). Returns: object

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools target clearly different outputs: transcript text versus video metadata. There is no realistic chance of an agent confusing them.

    Naming Consistency5/5

    Both tools use the same get_<noun> snake_case pattern, which is perfectly consistent.

    Tool Count3/5

    Two tools is thin for a server, though each one earns its place for a transcript-and-metadata use case. It feels more like a minimal utility than a full YouTube surface.

    Completeness3/5

    Core read operations for a single video are covered, but there is no way to search videos, list channel or playlist content, or discover videos, so agents cannot go from a topic to a video ID. For a read-only extraction tool this is workable but has notable gaps.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      An MCP server that enables users to retrieve YouTube transcripts and perform video or channel searches without requiring Google API keys. It supports transcript chunking and provides tools for detailed video content analysis and channel metadata extraction.
      5
      4
      MIT