AI agents call getRelatedVideos 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 performs a read-only retrieval of publicly available video recommendation data from YouTube. It queries the platform for related content and returns results without modifying any data, executing code, or affecting system state. The operation has minimal blast radius if misused by an AI agent—at worst, it would retrieve unexpected video recommendations.
From the tool's definition Tool name 'getRelatedVideos' and description 'Retrieves related videos' indicate a query operation with no side effects.
Attacks that exploit this kind of access
Retrieves related videos for a specific video. Returns a list of videos that are similar or related to the specified video, based on YouTube. 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 getRelatedVideos: 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.
getRelatedVideos 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 getRelatedVideos 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 getRelatedVideos. 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.
getRelatedVideos is provided by the Yt MCP server (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 →