Search for YouTube videos with advanced filtering options
AI agents call search_videos to retrieve information from YouTube Toolbox without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns video search results from YouTube. It has no side effects, does not modify data, does not execute arbitrary code or commands, and does not cause destructive changes. It is a standard read operation that queries YouTube's public video index. The 'advanced filtering options' are parameters for refining the search query, not capabilities that escalate this beyond a simple read operation.
From the tool's definition Tool name 'search_videos' and description 'Search for YouTube videos with advanced filtering options' indicate a query/retrieval operation with no modification or execution of external operations.
Documented attack patterns abuse exactly the kind of access search_videos gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and YouTube Toolbox, and nothing reaches the server without passing your rules. This is the rule we recommend for search_videos:
{
"version": "1",
"default": "deny",
"tools": {
"search_videos": {}
}
}search_videos 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.
Search for YouTube videos with advanced filtering options. It is categorised as a Read tool in the YouTube Toolbox MCP Server, which means it retrieves data without modifying state.
Register the YouTube Toolbox 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 YouTube Toolbox. 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 YouTube Toolbox MCP server (jikime/py-mcp-youtube-toolbox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from YouTube Toolbox, 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.
8 YouTube Toolbox tools catalogued and risk-classified — across an index of 43,000+ MCP servers.