Sign in Book a demo
Back to Tools
Search API Key BYOCPro
Build Your Agent View YouTube Documentation
youtube logo

YouTube MCP Tools for AI Agents

Let an agent search YouTube and retrieve video details for research, recommendations, and content workflows.

Available Tools

4 tools available in this integration

Youtube.GetVideo

Get details about a YouTube video.

Youtube.GetYoutubeVideoDetails

Get details about a YouTube video.

Youtube.SearchForVideos

Search for YouTube videos related to the query.

Youtube.SearchVideos

Search for YouTube videos related to the query.

Why agent-optimized tools matter

Built for intent, not API schemas

Ask the agent to "find the best YouTube videos explaining vector databases and compare them." Arcade picks the right YouTube actions without guessing video IDs before searching.

Up to 100x fewer tokens

YouTube search returns concise matching video records, and the agent fetches details only for videos worth inspecting, so it can narrow a result set without loading every video's information into context.

Complete the workflow end to end

Search videos, compare candidates, inspect selected details, summarize the findings, and return the links through one toolkit designed around the complete video research task.

Make actions predictable and controlled

Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.

Securing YouTube

The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.

This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.

Learn about Contextual Access Policies

For YouTube, you can implement some of these policies:

Access when tools are listed for a user
  • Decide which tools an agent is allowed to see at all. A tool that is never listed cannot be called, whoever is asking.
Pre-execution before each tool call
  • Inspect the inputs a call is about to run with, and block it or send it for human approval when they fall outside what the agent should do unsupervised.
Post-execution after the tool returns
  • Redact email addresses, phone numbers, and external contact links from Youtube.GetYoutubeVideoDetails results before the model sees video descriptions.
  • Strip email addresses and phone numbers from descriptions returned by Youtube.SearchForVideos so an agent cannot extract personal contact details from search results.

How to use YouTube with your agent

Pick your MCP client below and follow the setup from authentication to your first YouTube search. Then try the example prompts with your agent.

Your questions, answered

A YouTube MCP server exposes YouTube search and video-detail capabilities as structured tools that an AI agent can call through the Model Context Protocol. With Arcade, an agent can search for videos and inspect details about selected videos using the configured API access.

YouTube does not provide a first-party MCP server through this integration. Arcade provides the MCP access layer, authentication and credential brokering, plus agent-optimized search and video-detail actions with approval, redaction, and scope controls.

Arcade agents can search for videos related to a query and retrieve details about a specific video. The integration is read-only: agents cannot upload, edit, delete, comment on, like, or manage YouTube videos through it.

This integration uses a shared YouTube API key or secret configured once, rather than per-user OAuth permissions. The key must have access to the YouTube Data API operations needed for searching videos and retrieving video details.

No. Users do not each connect their own YouTube account for this integration. A shared API key or secret is configured once and brokered by Arcade rather than exposed to the model, so calls use that configured credential.

Yes. Contextual Access policies can require human approval before a consequential call, redact fields from responses, or hide the integration from an agent entirely. The YouTube actions here are read-only, so they do not publish or change video content.

Arcade proxies YouTube API calls and does not persist your content as part of normal tool execution. The configured credential is brokered and stored encrypted at rest, and the model never receives it.

Any framework or client that can connect to Arcade's MCP gateway or tool APIs works, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.

Arcade continues using the configured API key while it remains valid. If the key is revoked, rotated, expires, or can no longer be used, calls stop until the credential is reconnected or updated.

YouTube Data API quotas and rate limits apply to searches and video-detail requests made through Arcade. The available quota depends on the configured YouTube API project and its current limits.

Ready to actually ship your agent?

Connect your agent to YouTube with a shared API key, agent-optimized tools and approval controls for consequential actions.

Build Your Agent Read the YouTube Quickstart