AI agents call search_videos to retrieve information from Yt Fetch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a search and retrieval operation against YouTube's public video database. No data is created, modified, deleted, or destroyed. No code execution, external operations, or financial transactions occur. This is a standard Read operation with minimal risk—the worst outcome of misuse would be excessive API calls or information gathering about public videos.
From the tool's definition Tool description states 'Search YouTube for videos' which is a query/retrieval operation with no side effects. The 'filters and sorting options' are query parameters, not modifications.
Attacks that exploit this kind of access
Search YouTube for videos with various filters and sorting options. It is categorised as a Read tool in the Yt Fetch MCP Server, which means it retrieves data without modifying state.
Register the Yt Fetch MCP server in PolicyLayer and add a rule for search_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 Yt Fetch. Nothing to install.
search_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 search_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 search_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.
search_videos is provided by the Yt Fetch MCP server (smith-nathanh/yt-fetch). 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 →