Upload Videos to YouTube via CLI

YouTube Uploader MCP is a Model Context Protocol server that enables direct video uploads to YouTube from any MCP client (Claude Desktop, Cursor, VS Code, AnythingLLM) without using the YouTube Studio interface or command-line tools. It handles OAuth2 authentication locally, manages tokens across multiple channels, and provides tools for uploading videos with metadata control including titles, descriptions, tags, category settings, privacy options, scheduled publish times, custom thumbnails, playlist assignment, and subtitle attachment.

Use this connector when you want to upload videos to YouTube from within your AI workflow, generate video metadata (titles, descriptions, tags) using your LLM client, or manage multiple YouTube channels without switching contexts. It's designed for content creators who want to streamline publishing while keeping OAuth credentials local and never shared with third parties.

Do NOT use this if you need YouTube Studio's advanced features beyond what the upload and update_video tools provide. This server focuses on video upload and post-upload configuration tasks.

You provide a video file path, metadata (title, description, tags, category), privacy settings (public, private, unlisted), optional language settings, scheduled publish times, and post-upload assets like thumbnails (under 2MB) and subtitle files. The server requires a Google OAuth2 client_secret.json file from Google Developer Console.

The server provides six tools: authenticate (generates OAuth2 URL), accesstoken (exchanges code for credentials and channel info), channels (retrieves authenticated channels), refreshtoken (force-refreshes tokens), upload_video (uploads video file with main details), and update_video (manages post-upload configurations including playlist additions, thumbnail uploads, and subtitle attachments).

Compatible MCP clients include:

• Claude Desktop: Direct integration via MCP configuration for conversational video uploads
• Cursor: IDE-based video publishing workflow
• VS Code: Editor-integrated YouTube management
• AnythingLLM: Multi-model AI client support

Requires Google OAuth2 setup through Google Developer Console with the https://www.googleapis.com/auth/youtube.force-ssl scope for full functionality including subtitle uploads.

Single-command installation for Mac and Linux:

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/anwerj/youtube-uploader-mcp/master/scripts/install.sh)"

For Windows PowerShell:

Invoke-WebRequest -UseBasicParsing "https://raw.githubusercontent.com/anwerj/youtube-uploader-mcp/master/scripts/install.ps1" -OutFile "$env:TEMP\install.ps1"; PowerShell -NoProfile -ExecutionPolicy Bypass -File "$env:TEMP\install.ps1"

The installer downloads the OAuth client secret, sets permissions, updates Claude Desktop config automatically, and prints configuration for other MCP clients.

Manual configuration example:

{
  "mcpServers": {
    "youtube-uploader-mcp": {
      "command": "/absolute/path/to/youtube-uploader-mcp-<os>-<arch>",
      "args": [
        "-client_secret_file",
        "/absolute/path/to/client_secret.json(See Below)"
      ]
    }
  }
}

Content creators, video producers, and developers who publish to YouTube regularly and want to integrate uploads into AI-assisted workflows. Ideal for users managing multiple YouTube channels who need secure, local OAuth management without exposing credentials to LLMs or third-party services. The free, open-source approach suits creators who want control over their authentication flow and upload automation.