AI agents call get_normalized_url to retrieve information from Yt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool takes a YouTube URL as input and returns a normalized version of it. It performs no modifications to any data, executes no code, and triggers no external operations beyond simple URL parsing and formatting. It is a pure data retrieval and transformation function with no destructive, financial, or state-changing capabilities.
From the tool's definition Tool name 'get_normalized_url' and description 'Returns the normalized YouTube URL for a given URL' indicate a read-only operation that retrieves and formats data without side effects.
Attacks that exploit this kind of access
Returns the normalized YouTube URL for a given URL. It is categorised as a Read tool in the Yt MCP Server, which means it retrieves data without modifying state.
Register the Yt MCP server in PolicyLayer and add a rule for get_normalized_url: 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. Nothing to install.
get_normalized_url 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_normalized_url 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_normalized_url. 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_normalized_url is provided by the Yt MCP server (kdr/yt-mcp-server). 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 →