Skip to main content
Glama
Sign In
deenesjakoruzh
youtube-studio-mcp

youtube-studio-mcp

by Dhananjayrbiraris
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

YouTube Studio & Channel Analytics MCP Server

A Production-Grade Model Context Protocol (MCP) Server for YouTube Studio & Channel Intelligence

License: MIT Python: 3.11+ Managed by: uv MCP Compatible

Empower AI assistants (Claude, Cursor, Antigravity, etc.) to analyze your YouTube channel, track video metrics, deep-dive into YouTube Studio analytics, discover audience traffic sources, and analyze community sentiment — configured entirely through .env.

🚀 Features & MCP Tool Suite

YouTube Studio MCP provides 8 specialized tools:

Tool

Category

Description

get_channel_overview

Channel Stats

Returns channel title, handle, subscriber count, total lifetime views, video count, topic categories, and description.

get_channel_analytics

Studio Analytics

Queries core Studio metrics (views, watch time hours, average view duration, subscribers gained/lost, likes, shares, comments, impressions, CTR) over any timeframe (7d, 28d, 90d, 365d, last_month, or custom dates).

get_analytics_by_dimension

Demographics & Traffic

Detailed breakdowns by dimension: trafficSource (YouTube search, suggested, browse), deviceType, country, ageGroup, gender, operatingSystem, or day.

get_top_performing_videos

Video Intelligence

Ranks your top videos by views, watch time minutes, or subscribers gained in any date range.

get_video_analytics

Video Deep-Dive

Deep-dive analytics on a single specific video (daily trajectory, watch time, audience retention, traffic sources).

list_channel_videos

Content Inventory

Lists uploaded videos with current views, likes, comments, duration, and privacy status.

get_video_details

Video Metadata

Returns full metadata, tags, description, category, and statistics for specified video IDs.

get_video_comments

Community & Sentiment

Retrieves top comment threads and replies across your channel or on a specific video for sentiment analysis and feedback.

Related MCP server: youtube-organic-mcp

⚙️ Environment Configuration (.env)

All credentials and settings are read directly from .env:

# Google OAuth 2.0 Credentials (from Google Cloud Console)
YOUTUBE_CLIENT_ID=your_client_id.apps.googleusercontent.com
YOUTUBE_CLIENT_SECRET=your_client_secret

# OAuth Refresh Token (written automatically by run_auth.py)
YOUTUBE_REFRESH_TOKEN=

🛠️ Step-by-Step Setup Guide

1. Clone & Install Dependencies with uv

git clone https://github.com/Dhananjayrbiraris/youtube-mcp.git
cd youtube-mcp

uv venv
uv pip install -e .

2. Set Up Google Cloud Project (One-Time)

  1. Open Google Cloud Console.

  2. Create a new project (e.g. YouTube-Studio-MCP).

  3. In APIs & Services > Library, enable:

    • YouTube Data API v3

    • YouTube Analytics API

  4. In OAuth consent screen:

    • User Type: External -> fill app name & your email.

    • Under Test users, add your Google email address.

  5. In Credentials:

    • Click Create Credentials > OAuth client ID.

    • Application Type: Desktop App.

    • Copy the Client ID and Client Secret.

  6. Paste them into .env:

    YOUTUBE_CLIENT_ID=123456789-xxxx.apps.googleusercontent.com
YOUTUBE_CLIENT_SECRET=GOCSPX-xxxx

3. Run 1-Click Authenticator

uv run run_auth.py

This launches your browser for a 1-click Google OAuth login. It automatically writes the YOUTUBE_REFRESH_TOKEN directly into your .env file.

4. Connect to your AI Client

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "youtube-studio": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/youtube-mcp",
        "run",
        "youtube-studio-mcp"
      ]
    }
  }
}

💡 Example AI Prompts

  • "Give me an overview of my YouTube channel's performance over the last 28 days."

  • "Where is most of my traffic coming from (search, suggested videos, or browse features)?"

  • "Which of my videos generated the most subscribers this month?"

  • "Summarize common themes and questions from the comments on my latest video."

  • "Show me my audience breakdown by age group and country."

🧪 Testing

Run the test suite:

pytest

📄 License

This project is licensed under the MIT License.

Available Tools

8 tools
get_analytics_by_dimensionA

Fetches channel analytics broken down by a specific dimension.

Args: dimension: The dimension to analyze. Supported values: - 'trafficSource' (YouTube search, suggested videos, browse features, external, etc.) - 'deviceType' (mobile phone, computer, TV, tablet) - 'country' (top geographic viewer locations) - 'ageGroup' (demographics: 18-24, 25-34, 35-44, etc.) - 'gender' (viewer gender percentage) - 'operatingSystem' (Android, Windows, iOS, etc.) - 'day' or 'month' time_period: Preset time period ('7d', '28d', '90d', '365d', 'last_month'). Defaults to '28d'. start_date: Optional explicit start date (YYYY-MM-DD). end_date: Optional explicit end date (YYYY-MM-DD). max_results: Maximum number of rows to return (default: 20).

Returns: A ranked list of metrics for each dimension value.

Inputs: dimension (required), end_date, start_date, max_results, +1 more. Returns: result

get_channel_analyticsA

Queries core YouTube Studio channel analytics for a specified timeframe.

Args: time_period: Preset time period ('7d', '28d', '90d', '365d', 'last_month'). Defaults to '28d'. start_date: Explicit start date in YYYY-MM-DD format (overrides time_period if both start & end are provided). end_date: Explicit end date in YYYY-MM-DD format. dimensions: Dimension to group by, e.g. 'day' (default) or None for a single aggregate row.

Returns: Summary metrics (total views, watch time hours, avg view duration, subscribers gained/lost, net growth, likes, shares, comments, impressions, CTR) and daily time-series data points.

Inputs: end_date, dimensions, start_date, time_period. Returns: result

get_channel_overviewA

Fetches high-level metadata and lifetime statistics for your YouTube channel.

Returns channel title, handle, subscriber count, total lifetime views, video count, creation date, topic categories, and channel description.

Inputs: no named parameters. Returns: result

get_top_performing_videosA

Identifies and ranks your top-performing videos within a time period.

Args: time_period: Preset time period ('7d', '28d', '90d', '365d', 'last_month'). Defaults to '28d'. start_date: Optional explicit start date (YYYY-MM-DD). end_date: Optional explicit end date (YYYY-MM-DD). order_by: Metric to rank by: 'views', 'estimatedMinutesWatched', 'subscribersGained', or 'likes'. max_results: Number of top videos to return (default: 10).

Returns: Ranked list of videos with title, duration, period views, watch time, subscribers gained, and lifetime views.

Inputs: end_date, order_by, start_date, max_results, +1 more. Returns: result

get_video_analyticsA

Performs deep-dive analytics on a single specific video.

Args: video_id: The 11-character YouTube video ID (e.g. 'dQw4w9WgXcQ'). time_period: Preset time period ('7d', '28d', '90d', '365d', 'last_month'). Defaults to '28d'. start_date: Optional explicit start date (YYYY-MM-DD). end_date: Optional explicit end date (YYYY-MM-DD).

Returns: Video metadata, daily trajectory, total period views & watch time, and traffic source breakdown for this specific video.

Inputs: video_id (required), end_date, start_date, time_period. Returns: result

get_video_commentsA

Fetches comment threads and audience discussions for a video or the whole channel.

Args: video_id: Optional specific YouTube video ID. If omitted, retrieves recent comments across the channel. max_results: Number of comment threads to fetch (max 100). order: Sort order: 'relevance' (top comments) or 'time' (newest first).

Returns: List of comments with author, comment text, likes, timestamp, and sample replies.

Inputs: order, video_id, max_results. Returns: result

get_video_detailsA

Fetches full metadata, description, tags, and statistics for specified video IDs.

Args: video_ids: Comma-separated list of YouTube video IDs (e.g. 'vid1,vid2').

Returns: Complete video details including title, description, tags, topic categories, view/like/comment counts, duration, and content settings.

Inputs: video_ids (required). Returns: result

list_channel_videosA

Lists your channel's uploaded videos in reverse chronological order.

Args: max_results: Number of videos to retrieve (max 50 per page). page_token: Optional page token for pagination.

Returns: List of videos with video ID, title, publish date, duration, views, likes, comments, and privacy status.

Inputs: page_token, max_results. Returns: result

Tool Schema Changelog

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

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.9/5.0

    Scored across 8 tools

    Disambiguation3/5

    There are several analytics tools with overlapping parameters and outputs: get_channel_analytics can group by day, which overlaps with get_analytics_by_dimension, and get_top_performing_videos overlaps with list_channel_videos in returning video statistics. However, each tool's detailed description clarifies the intended focus (summary vs dimension vs ranked list), so agents can generally disambiguate.

    Naming Consistency4/5

    All tools use snake_case and nearly all start with get_, with list_channel_videos as the only list_ exception. The pattern is easily predictable, though get_top_performing_videos and get_analytics_by_dimension are phrase-style names rather than clean verb_noun resource names.

    Tool Count5/5

    Eight tools is a well-scoped size for a YouTube Studio analytics server; each tool covers a distinct reporting need without redundancy or bloat. This is within the ideal range and doesn't overwhelm an agent.

    Completeness4/5

    The toolset provides solid read-only coverage of channel analytics, video metadata/performance, and comments, supporting common creator reporting workflows. Notable gaps exist for video-level dimension breakdowns beyond traffic source and any management actions, but given the analytics-focused descriptions, these are minor.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    Appeared in Searches