inspect_url_tool
AI agents call inspect_url_tool to retrieve information from MCP Google Search Console without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query operation to inspect and retrieve information about a specific URL from Google Search Console. No side effects, modifications, deletions, or financial transactions occur. While the description is empty, the name and server context strongly indicate a data retrieval function typical of analytics platforms.
From the tool's definition Tool name 'inspect_url_tool' indicates inspection/retrieval of URL data. The server description describes 'URL inspection' as part of analytics and analysis capabilities.
Attacks that exploit this kind of access
inspect_url_tool. It is categorised as a Read tool in the MCP Google Search Console MCP Server, which means it retrieves data without modifying state.
Register the MCP Google Search Console MCP server in PolicyLayer and add a rule for inspect_url_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 MCP Google Search Console. Nothing to install.
inspect_url_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 inspect_url_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 inspect_url_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.
inspect_url_tool is provided by the MCP Google Search Console MCP server (crunchtools/mcp-google-search-console). 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 →