get_video

THE RISK

Low Risk

Why get_video needs a policy

This tool retrieves and returns video metadata and summaries from YouTube, which is a read-only operation with no side effects. It queries existing data without creating, modifying, deleting, or executing any actions. The blast radius of misuse is minimal - an attacker could gather information about videos but cannot alter data or trigger external operations.

From the tool's definition Tool description states 'Get video metadata + summary' - a retrieval operation that reads and returns information about a YouTube video. No modification, deletion, execution, or financial transaction occurs.

Documented attack patterns abuse exactly the kind of access get_video gives an agent:

POLICY

How to control get_video

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP YouTube Intelligence, and nothing reaches the server without passing your rules. This is the rule we recommend for get_video:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_video": {}
  }
}

get_video is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register MCP YouTube Intelligence — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP YouTube Intelligence tools

Read extract_entities Extract structured entities (companies, indices, people, sectors, etc.) from a video trans Read get_comments Get top comments for a video. Optionally summarize them. Read get_playlist Get playlist metadata and video list from a YouTube playlist. Read get_transcript Get video transcript. mode: Read monitor_channel Monitor a YouTube channel via RSS. action: Read search_transcripts Search stored transcripts by keyword. Returns matching snippets. Read search_youtube Search YouTube videos by keyword. Returns metadata list (~200 tokens). Read segment_topics Segment a video transcript into topics based on transition markers.

All 10 MCP YouTube Intelligence tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get_video

What does the get_video tool do? +

Get video metadata + summary (~300 tokens). Provide a YouTube video ID. It is categorised as a Read tool in the MCP YouTube Intelligence MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_video? +

Register the MCP YouTube Intelligence MCP server in PolicyLayer and add a rule for get_video: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP YouTube Intelligence. Nothing to install.

What risk level is get_video? +

get_video is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_video? +

Yes. Add a rate_limit block to the get_video rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block get_video completely? +

Set action: deny in the PolicyLayer policy for get_video. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides get_video? +

get_video is provided by the MCP YouTube Intelligence MCP server (janghyuckyun/mcp-youtube-intelligence). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP YouTube Intelligence tool call.

Start from MCP YouTube Intelligence, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →