Fetches video metadata: title, channel, description, publish date, views, duration.
AI agents call get_metadata to retrieve information from Youtube without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves publicly available video information without side effects. It performs a read-only query operation comparable to viewing video details on YouTube's public interface. The data returned is metadata only, not sensitive credentials or private content. Severity is low because misuse would yield only public information already accessible via standard YouTube browsing.
From the tool's definition Tool description explicitly states it 'Fetches video metadata' (title, channel, description, publish date, views, duration) with no modification, deletion, or execution capability mentioned.
Documented attack patterns abuse exactly the kind of access get_metadata gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Youtube, and nothing reaches the server without passing your rules. This is the rule we recommend for get_metadata:
{
"version": "1",
"default": "deny",
"tools": {
"get_metadata": {}
}
}get_metadata 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.
Fetches video metadata: title, channel, description, publish date, views, duration. It is categorised as a Read tool in the Youtube MCP Server, which means it retrieves data without modifying state.
Register the Youtube MCP server in PolicyLayer and add a rule for get_metadata: 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. Nothing to install.
get_metadata 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_metadata 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_metadata. 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_metadata is provided by the Youtube MCP server (umbertotancorre/youtube-mcp-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Youtube, 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.
11 Youtube tools catalogued and risk-classified — across an index of 43,000+ MCP servers.