Preview mode: Use AI to identify important moments in a YouTube video and return their timestamps WITHOUT extracting frames. Use this to preview what timestamps would be selected before committing to extraction.
AI agents call get_video_timestamps 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 only retrieves and analyzes metadata (timestamps) from publicly accessible YouTube videos. It has no side effects, does not modify any data, does not execute arbitrary code on the user's system, and does not commit financial or destructive actions. The 'preview mode' framing further emphasizes it is informational only. Classification as Read is appropriate with high confidence.
From the tool's definition Tool description states it uses AI to 'identify important moments in a YouTube video and return their timestamps WITHOUT extracting frames.' The explicit mention of 'WITHOUT extracting frames' and 'preview mode' confirms this is a read-only operation that…
Attacks that exploit this kind of access
Preview mode: Use AI to identify important moments in a YouTube video and return their timestamps WITHOUT extracting frames. Use this to preview what timestamps would be selected before committing to extraction. 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 get_video_timestamps: 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.
get_video_timestamps 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_timestamps 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_timestamps. 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_timestamps is provided by the Yt MCP server (pakmangames/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 →