Downloads the transcript of a YouTube video as a markdown file (.md) with timestamps. Returns the file path.
AI agents call download_transcript_timed to retrieve information from Youtube without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a retrieval operation that queries YouTube video data and exports it locally. It has no side effects on YouTube, the video, or any systems. The action is read-only—fetching public transcript data. Severity is low because unauthorized transcript download presents minimal risk: transcripts are typically public metadata, and downloading them does not alter state, execute code, or commit financial actions.
From the tool's definition Tool downloads and retrieves a transcript with timestamps as a markdown file. The verb 'download' here means 'fetch/retrieve' (similar to sibling tools like 'get_transcript' and 'get_transcript_timed').
Documented attack patterns abuse exactly the kind of access download_transcript_timed gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Youtube, and nothing reaches the server without passing your rules. This is the rule we recommend for download_transcript_timed:
{
"version": "1",
"default": "deny",
"tools": {
"download_transcript_timed": {}
}
} download_transcript_timed is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Downloads the transcript of a YouTube video as a markdown file (.md) with timestamps. Returns the file path. It is categorised as a Read tool in the Youtube MCP Server, which means it retrieves data without modifying state.
Register the Youtube MCP server in PolicyLayer and add a rule for download_transcript_timed: 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. Nothing to install.
download_transcript_timed 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 download_transcript_timed 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 download_transcript_timed. 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.
download_transcript_timed is provided by the Youtube MCP server (umbertotancorre/youtube-mcp-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Youtube, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
11 Youtube tools catalogued and risk-classified — across an index of 43,000+ MCP servers.