check_backend_health
AI agents call check_backend_health to retrieve information from Restaurant Backend MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Health checks are diagnostic operations that only retrieve and report the current operational status of a backend service. They have no side effects, do not modify data, and pose minimal risk even if invoked repeatedly or erroneously. The blank description lowers confidence slightly, but the name's semantic meaning is sufficiently clear to classify this as a benign Read operation.
From the tool's definition Tool name 'check_backend_health' indicates a health check operation, which typically queries system status without modifying data. No description provided, but health checks are universally read-only operations that retrieve status information.
Attacks that exploit this kind of access
check_backend_health. It is categorised as a Read tool in the Restaurant Backend MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Restaurant Backend MCP Server MCP server in PolicyLayer and add a rule for check_backend_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 Restaurant Backend MCP Server. Nothing to install.
check_backend_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 check_backend_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 check_backend_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.
check_backend_health is provided by the Restaurant Backend MCP Server MCP server (pasanis/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 →