GET /api/v1/transcripts/{video_id}. Get full transcript for a video.
AI agents call get_transcript to retrieve information from Youtube Transcript without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves transcript data from an existing video without creating, modifying, or deleting anything. It is a straightforward query operation that returns information. The severity is low because transcript retrieval poses minimal risk; transcripts are typically public or user-owned content, and reading them cannot cause adverse side effects like data loss or unauthorized changes.
From the tool's definition Tool description explicitly states 'Get full transcript for a video' — a retrieval operation with no modification or deletion. The HTTP method is GET, a read-only operation.
Attacks that exploit this kind of access
GET /api/v1/transcripts/{video_id}. Get full transcript for a video. It is categorised as a Read tool in the Youtube Transcript MCP Server, which means it retrieves data without modifying state.
Register the Youtube Transcript MCP server in PolicyLayer and add a rule for 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 Youtube Transcript. Nothing to install.
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 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 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.
get_transcript is provided by the Youtube Transcript MCP server (youtube-transcript-dev/youtube-transcript-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 →