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 OpenAI Agents SDK 4 tools — connect in under 2 minutes

Name: YouTube
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 4 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect YouTube through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

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 agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="YouTube Assistant",
            instructions=(
                "You help users interact with YouTube. "
                "You have access to 4 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from YouTube"
        )
        print(result.final_output)

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.

The OpenAI Agents SDK auto-discovers all 4 tools from YouTube through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries YouTube, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

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 OpenAI Agents SDK 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 OpenAI Agents SDK via MCP

Follow these steps to integrate the YouTube MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 4 tools from YouTube

Why Use OpenAI Agents SDK with the YouTube MCP Server

OpenAI Agents SDK provides unique advantages when paired with YouTube through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

YouTube + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the YouTube MCP Server delivers measurable value.

Automated workflows: build agents that query YouTube, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries YouTube, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through YouTube tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query YouTube to resolve tickets, look up records, and update statuses without human intervention

YouTube MCP Tools for OpenAI Agents SDK (4)

These 4 tools become available when you connect YouTube to OpenAI Agents SDK 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 OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK 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 OpenAI Agents SDK

Common issues when connecting YouTube to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

YouTube + OpenAI Agents SDK FAQ

Common questions about integrating YouTube MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.