AI agents call get_video_metadata_tool to retrieve information from YtMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries YouTube video metadata without side effects. It performs a passive data lookup operation that does not create, modify, delete, or execute anything. The server is explicitly designed for read-only access to YouTube data. Risk is minimal as metadata exposure is publicly available information.
From the tool's definition Tool description states it 'Extract[s] comprehensive metadata for a YouTube video' with no mention of modification, deletion, or execution. Server description emphasizes 'read-only access' and 'metadata retrieval'.
Attacks that exploit this kind of access
Extract comprehensive metadata for a YouTube video. It is categorised as a Read tool in the YtMCP MCP Server, which means it retrieves data without modifying state.
Register the Yt MCP server in PolicyLayer and add a rule for get_video_metadata_tool: 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 YtMCP. Nothing to install.
get_video_metadata_tool 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_video_metadata_tool 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_video_metadata_tool. 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_video_metadata_tool is provided by the Yt MCP server (utkarshchaudhary009/ytmcp). 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 →