AI agents call comet_poll 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 queries the status of running agentic tasks but does not execute commands, modify data, delete resources, or move money. It is a passive observation mechanism for tracking progress. The repeated calling pattern is typical of status checks in async systems. No side effects are produced by invoking this tool.
From the tool's definition Tool name 'comet_poll' and description 'Check agent status and progress. Call repeatedly to monitor agentic tasks.' indicate a polling/monitoring operation that retrieves status information without modifying state.
Attacks that exploit this kind of access
Check agent status and progress. Call repeatedly to monitor agentic tasks. 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_poll: 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_poll 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_poll 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_poll. 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_poll 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 →