Can I see how many likes and views a video has through the agent?

Yes. The `get_video_details` tool allows your AI agent to retrieve full real-time statistics for any YouTube video ID, including view counts, like counts, and the total number of comments.

How do I find out the subscriber count for a specific channel?

You can use the `get_channel_details` tool. Provide the unique channel ID, and your agent will return the channel's performance statistics, including subscriber counts, total views, and video counts.

Is it possible to read the comments on a video via chat?

Absolutely. Use the `list_video_comments` tool to retrieve the top most relevant or recent comment threads from any video ID, helping you perform rapid sentiment analysis through conversation.

YouTube MCP Server for Pydantic AI 4 tools — connect in under 2 minutes

Name: YouTube
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 4 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect YouTube through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to YouTube "
            "(4 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in YouTube?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About YouTube MCP Server

Connect your YouTube Data API account to any AI agent and harness the power of global video intelligence through natural conversation.

Pydantic AI validates every YouTube tool response against typed schemas, catching data inconsistencies at build time. Connect 4 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Universal Search — Find relevant video content by keyword or exact phrase, retrieving a list of metadata including titles and descriptions
Deep Video Insights — Retrieve full technical metadata for specific videos, including view counts, like counts, and engagement statistics
Channel Performance — Monitor any YouTube channel's branding and statistics, including total subscriber counts and video volume
Sentiment Analysis — Fetch the most relevant comments from any video to analyze user feedback and community engagement
Content Discovery — Quickly find unique video and channel IDs required for automated media monitoring workflows
Trend Auditing — Browse and analyze video descriptions and statistics to identify content patterns and audience interests
Metadata Retrieval — Get high-resolution thumbnails and precise upload timestamps for any piece of video content

The YouTube MCP Server exposes 4 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect YouTube to Pydantic AI via MCP

Follow these steps to integrate the YouTube MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 4 tools from YouTube with type-safe schemas

Why Use Pydantic AI with the YouTube MCP Server

Pydantic AI provides unique advantages when paired with YouTube through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your YouTube integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your YouTube connection logic from agent behavior for testable, maintainable code

YouTube + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the YouTube MCP Server delivers measurable value.

Type-safe data pipelines: query YouTube with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple YouTube tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query YouTube and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock YouTube responses and write comprehensive agent tests

YouTube MCP Tools for Pydantic AI (4)

These 4 tools become available when you connect YouTube to Pydantic AI via MCP:

get_channel

Retrieves complete statistics and branding information for a YouTube channel

get_video

Retrieves full metadata, description, and statistics for a specific YouTube video

list_comments

Returns the most recent/relevant comment threads. Fetches the top most relevant comments from a specific YouTube video

search_videos

Returns a list of video metadata including titles and descriptions. Search for YouTube videos by keyword or exact phrase

Example Prompts for YouTube in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with YouTube immediately.

"Search YouTube for 'generative AI tutorials' and show me the top 5 results."

"What are the statistics for video ID 'dQw4w9WgXcQ'?"

"Check the subscriber count for channel ID 'UC_x5XG1OV2P6uYZ5M1D2ogw'."

Troubleshooting YouTube MCP Server with Pydantic AI

Common issues when connecting YouTube to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

YouTube + Pydantic AI FAQ

Common questions about integrating YouTube MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your YouTube MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.