Return which tools are available based on current configuration.
AI agents call get_capabilities to retrieve information from Youtube Research without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is an introspection tool that passively reads system state (available tools/capabilities) and returns the information. It has no side effects, does not modify data, does not execute external operations, and does not commit financial or destructive actions. It is a straightforward Read category tool with minimal security risk.
From the tool's definition Tool name 'get_capabilities' and description 'Return which tools are available' indicate a query operation that retrieves configuration information without modifying any data or triggering external operations.
Documented attack patterns abuse exactly the kind of access get_capabilities gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Youtube Research, and nothing reaches the server without passing your rules. This is the rule we recommend for get_capabilities:
{
"version": "1",
"default": "deny",
"tools": {
"get_capabilities": {}
}
}get_capabilities 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.
Return which tools are available based on current configuration. It is categorised as a Read tool in the Youtube Research MCP Server, which means it retrieves data without modifying state.
Register the Youtube Research MCP server in PolicyLayer and add a rule for get_capabilities: 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 Research. Nothing to install.
get_capabilities 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_capabilities 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_capabilities. 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_capabilities is provided by the Youtube Research MCP server (lee-s-dev/youtube-research-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Youtube Research, 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.
10 Youtube Research tools catalogued and risk-classified — across an index of 43,000+ MCP servers.