AI agents invoke youtube_download_video to trigger actions in Google. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool name suggests downloading a YouTube video, which constitutes an external operation (fetching and storing content) beyond simple read/query. Downloading can have storage, legal, and copyright implications. The description is empty, which lowers confidence, but the name strongly implies an Execute-level action (triggering a download operation) rather than a simple metadata read.
From the tool's definition Tool name: 'youtube_download_video' — implies downloading video content from YouTube, which triggers an external operation with local side effects
Attacks that exploit this kind of access
youtube_download_video. It is categorised as a Execute tool in the Google MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Google MCP server in PolicyLayer and add a rule for youtube_download_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 Google. Nothing to install.
youtube_download_video is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the youtube_download_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.
Set action: deny in the PolicyLayer policy for youtube_download_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.
youtube_download_video is provided by the Google MCP server (psckeithw/mcp-google). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →