AI agents call youtube_list_playlist_videos to retrieve information from Google without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves publicly accessible playlist video metadata. It does not create, modify, delete, or execute operations. The only conceivable risk is information disclosure (e.g., discovering unlisted playlist contents), which is minimal and inherent to read access. Severity is low because playlist metadata is typically non-sensitive; even if sensitive, read-only access poses limited harm.
From the tool's definition Tool name contains 'list' and description states 'List all videos in a YouTube playlist' — a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List all videos in a YouTube playlist. It is categorised as a Read tool in the Google MCP Server, which means it retrieves data without modifying state.
Register the Google MCP server in PolicyLayer and add a rule for youtube_list_playlist_videos: 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 Google. Nothing to install.
youtube_list_playlist_videos 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 youtube_list_playlist_videos 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 youtube_list_playlist_videos. 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.
youtube_list_playlist_videos is provided by the Google MCP server (psckeithw/mcp-google). 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 →