Download the full spoken transcript of a YouTube video as clean plain text using yt-dlp — no API credentials required. Tries manual English captions first (or specified language_code), then auto-generated, then falls back to the first available language. Returns concatenated plain text plus metad...
AI agents call get_video_transcript to retrieve information from Ytmcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though get_video_transcript only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Download the full spoken transcript of a YouTube video as clean plain text using yt-dlp — no API credentials required. Tries manual English captions first (or specified language_code), then auto-generated, then falls back to the first available language. Returns concatenated plain text plus metadata about which language and caption type was used. Ideal for content research without consuming YouTube API quota. It is categorised as a Read tool in the Ytmcp MCP Server, which means it retrieves data without modifying state.
Register the Yt MCP server in PolicyLayer and add a rule for get_video_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 Ytmcp. Nothing to install.
get_video_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_video_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_video_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_video_transcript is provided by the Yt MCP server (@mrsknetwork/ytmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.