Explain cleanup and auto-cleanup policy gates for one PID. It never terminates processes.
AI agents call policy_explain to retrieve information from Clean Process Ended without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only reads and explains policy information for a given PID. It explicitly states it never terminates processes, making it a pure read/query operation with no side effects. Misuse potential is minimal as it only surfaces informational output.
From the tool's definition 'Explain cleanup and auto-cleanup policy gates for one PID. It never terminates processes.'
Attacks that exploit this kind of access
Explain cleanup and auto-cleanup policy gates for one PID. It never terminates processes. It is categorised as a Read tool in the Clean Process Ended MCP Server, which means it retrieves data without modifying state.
Register the Clean Process Ended MCP server in PolicyLayer and add a rule for policy_explain: 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 Clean Process Ended. Nothing to install.
policy_explain 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 policy_explain 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 policy_explain. 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.
policy_explain is provided by the Clean Process Ended MCP server (marcelocaporale/clean-process-ended). 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 →