AI agents call youtube_get_transcript to retrieve information from Google without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a straightforward data retrieval operation on YouTube video transcripts/captions. This has no side effects, does not execute code, does not modify or delete data, and does not involve financial transactions.
From the tool's definition Tool name and description indicate retrieval of existing data: 'Get transcript/captions for a YouTube video.' This is a read-only query operation that retrieves publicly available video metadata without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Get transcript/captions for a YouTube video. It is categorised as a Read tool in the Google MCP Server, which means it retrieves data without modifying state.
Register the Google MCP server in PolicyLayer and add a rule for youtube_get_transcript: 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_get_transcript is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the youtube_get_transcript 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_get_transcript. 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_get_transcript 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 →