How to Use the YouTube MCP in Mastra AI

Q: Can Mastra AI handle YouTube video metadata retrieval?

Absolutely. Use the getvideo tool within your workflow engine. It pulls all necessary stats and descriptions for a specific video, which is essential data for content analysis.

Q: How do I monitor multiple YouTube channels with Mastra AI?

You chain together calls to getchannel for every channel you want to audit. Since the framework supports automatic retries and failure handling, it makes running large batches of audits reliable.

Q: Does this MCP Server support YouTube comment analysis with Mastra AI?

Yes. You use listcomments as a tool within your workflow. The agent can gather the comments and then pass that thread data to another module for sentiment scoring or categorization.

Q: If my search fails for YouTube videos, how does Mastra AI help?

Mastra AI automatically retries the searchvideos tool using exponential backoff. This means your workflow is resilient and doesn't fail just because of a temporary API hiccup.

Build complex YouTube workflows that self-correct with Mastra AI.

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 Mastra AI

Create your Vinkius account to connect YouTube to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Channel Auditing

The `get_channel` tool retrieves full statistics and branding information for a given YouTube channel. You can build a workflow where the agent first checks this data, then conditionally routes based on performance thresholds. If the stats fall below an acceptable level, your Mastra AI workflow automatically triggers a notification step or initiates a retrial with different parameters.

Content Gap Analysis

Use `search_videos` to list videos by keyword. This tool finds potential content ideas across YouTube. You can wrap this in a multi-step workflow that collects dozens of titles and descriptions for later human review. This setup is ideal because if the initial search fails or times out, Mastra AI handles the backoff retry automatically, ensuring your pipeline doesn't break.

Comprehensive Video Performance Check

To audit a specific YouTube video, you combine `get_video` (for metadata and stats) with `list_comments`. The agent runs both tools sequentially. This allows for complex analysis: fetching the raw data from the first tool, passing it into the second, and then using conditional logic to generate a final report.

Setup guide

Set up YouTube MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All YouTube tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "youtube-mcp-client",
  servers: {
    "youtube-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "YouTube Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to YouTube tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent YouTube transactions"
);
console.log(result.text);

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 Mastra AI

Absolutely. Use the `get_video` tool within your workflow engine. It pulls all necessary stats and descriptions for a specific video, which is essential data for content analysis.

You chain together calls to `get_channel` for every channel you want to audit. Since the framework supports automatic retries and failure handling, it makes running large batches of audits reliable.

Yes. You use `list_comments` as a tool within your workflow. The agent can gather the comments and then pass that thread data to another module for sentiment scoring or categorization.

The server handles public-facing statistics, metadata, and comment threads. This data is structured for use in complex workflows within Mastra AI.

Mastra AI automatically retries the `search_videos` tool using exponential backoff. This means your workflow is resilient and doesn't fail just because of a temporary API hiccup.

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