AI agents call getTranscripts to retrieve information from Yt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that fetches existing video transcript data. It does not create, modify, delete, or execute any operations. The transcripts are already publicly available or licensed data being retrieved, making this a straightforward Read category tool with low severity, as transcript data is typically non-sensitive informational content.
From the tool's definition Tool description states it 'Retrieves transcripts for multiple videos. Returns the text content of videos' - retrieval with no modification or deletion.
Attacks that exploit this kind of access
Retrieves transcripts for multiple videos. Returns the text content of videos. It is categorised as a Read tool in the Yt MCP Server, which means it retrieves data without modifying state.
Register the Yt MCP server in PolicyLayer and add a rule for getTranscripts: 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 Yt. Nothing to install.
getTranscripts 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 getTranscripts 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 getTranscripts. 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.
getTranscripts is provided by the Yt MCP server (yt-mcp). 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 →