AI agents call service_health to retrieve information from Run402 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query that checks service availability/health status. It retrieves information about system state with no side effects, no data modification, and no external operation triggers. The low severity reflects that misuse would only expose operational metrics, not cause harm to infrastructure or data.
From the tool's definition Tool name 'service_health' and description 'Liveness check for the Run402 SERVICE' indicate a status query operation. The tool explicitly retrieves service health status without modifying any data or triggering external operations.
Attacks that exploit this kind of access
Liveness check for the Run402 SERVICE — not your organization. For your organization status (allowance, tier, projects), use. It is categorised as a Read tool in the Run402 MCP Server, which means it retrieves data without modifying state.
Register the Run402 MCP server in PolicyLayer and add a rule for service_health: 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 Run402. Nothing to install.
service_health 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_health 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_health. 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_health is provided by the Run402 MCP server (kychee-com/run402). 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 →