AI agents call service_url_tool to retrieve information from Infra without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs DNS resolution and an HTTP probe to check liveness — purely a read/query operation with no side effects on infrastructure state.
From the tool's definition "Resolve <service>.<INFRA_PUBLIC_DOMAIN> and probe its HTTP status. Quick liveness check."
Attacks that exploit this kind of access
Resolve <service>.<INFRA_PUBLIC_DOMAIN> and probe its HTTP status. Quick liveness check. It is categorised as a Read tool in the Infra MCP Server, which means it retrieves data without modifying state.
Register the Infra MCP server in PolicyLayer and add a rule for service_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 Infra. Nothing to install.
service_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 service_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 service_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.
service_url_tool is provided by the Infra MCP server (odanree/infra-mcp). 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 →