AI agents call comet_health to retrieve information from Comet without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs health monitoring and status checks of the MCP Comet connection. Monitoring and diagnostic queries are non-destructive read operations that retrieve status information without modifying, executing commands on external systems, or triggering irreversible actions.
From the tool's definition Tool name is 'comet_health' and description indicates it 'Check[s] MCP Comet connection health and auto-recover if it'. The verb 'check' is a diagnostic query operation with no side effects on data or system state.
Attacks that exploit this kind of access
Check MCP Comet connection health and auto-recover if it. It is categorised as a Read tool in the Comet MCP Server, which means it retrieves data without modifying state.
Register the Comet MCP server in PolicyLayer and add a rule for comet_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 Comet. Nothing to install.
comet_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 comet_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 comet_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.
comet_health is provided by the Comet MCP server (simplicianokelly52/comet_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 →