How to Use the YouTube MCP in Claude Code

Q: How do I monitor YouTube channel growth using Claude Code?

You run a scheduled job calling getchannel to pull the current subscriber count. You pipe this output into your monitoring script, which flags any sudden drops or spikes in metrics.

Q: Can Claude Code fetch video details for YouTube content?

Yes. Use getvideo. This tool fetches full metadata and stats based on a specific ID, providing structured output that's ideal for scripting purposes in your terminal session.

Q: What data types can Claude Code handle from YouTube?

Claude Code handles channel statistics (getchannel), individual video metadata (getvideo), and lists of comment threads (listcomments). The output is always standard text or JSON, ready for piping.

Automate YouTube audits and data piping using Claude Code in headless pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect YouTube MCP to Claude Code

Create your Vinkius account to connect YouTube to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup YouTube with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Script channel performance checks

Run `get_channel` to pull all the core statistics and branding info for a specified YouTube channel. You can pipe this output directly into a logging service or another script for automated reporting. This is perfect for CI/CD pipelines where you need to check if a channel's view count exceeded a threshold without needing a GUI.

Extract video metadata via CLI

Use `get_video` to get full metadata and stats for any YouTube video. The output is clean, machine-readable data that you can pipe into `jq` or another command-line utility. This lets your script audit content details—like the description text or view count—as part of a larger automated workflow.

Process comment threads for analysis

To analyze user feedback, run `list_comments` on a YouTube video. This tool returns structured data containing recent and relevant comment threads. You can capture this raw output and feed it into other text processing tools in your shell script.

Setup guide

Set up YouTube MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see youtube-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest YouTube transactions." It will automatically discover and invoke the available YouTube tools.

Terminal

claude mcp add --transport http youtube-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the YouTube MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "youtube-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by YouTube. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect YouTube now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about YouTube MCP in Claude Code

You run a scheduled job calling `get_channel` to pull the current subscriber count. You pipe this output into your monitoring script, which flags any sudden drops or spikes in metrics.

Yes. Use `get_video`. This tool fetches full metadata and stats based on a specific ID, providing structured output that's ideal for scripting purposes in your terminal session.

Claude Code handles channel statistics (`get_channel`), individual video metadata (`get_video`), and lists of comment threads (`list_comments`). The output is always standard text or JSON, ready for piping.

No. It's designed for headless execution. You connect it via SSH or within a Docker container, and all calls are handled through standard input/output (stdio) pipes.

The server touches channel performance statistics, video metadata, and comment thread content. All this raw data is accessible via the MCP Server's API endpoints.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript