AI agents call platform.health to retrieve information from CIVITAE without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a monitoring/diagnostic read operation that retrieves platform state information only. It has no capacity to modify, delete, or execute code. The stated purpose is to verify platform availability before other operations, which is a benign reconnaissance activity typical of health checks.
From the tool's definition Tool name 'platform.health' and description 'Returns ok status, version, and uptime' indicate a status query with no side effects or data modification.
Attacks that exploit this kind of access
Platform health check. Returns ok status, version, and uptime. Call before heavy operations to verify platform is up. It is categorised as a Read tool in the CIVITAE MCP Server, which means it retrieves data without modifying state.
Register the CIVITAE MCP server in PolicyLayer and add a rule for platform.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 CIVITAE. Nothing to install.
platform.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 platform.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 platform.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.
platform.health is provided by the CIVITAE MCP server (pypi:civitae-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
platform.health is one line of CIVITAE's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →