Plan cleanup for managed processes only. This is dry-run only and never terminates processes.
AI agents call managed_cleanup_dryrun 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.
A dry-run that plans but never acts is purely a read/inspection operation. It retrieves and analyzes process state to produce a cleanup plan, with no side effects on running processes. Misuse potential is minimal since no processes can be affected.
From the tool's definition 'This is dry-run only and never terminates processes' — the tool only plans cleanup without executing any termination or modification.
Attacks that exploit this kind of access
Plan cleanup for managed processes only. This is dry-run only and 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 managed_cleanup_dryrun: 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.
managed_cleanup_dryrun 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 managed_cleanup_dryrun 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 managed_cleanup_dryrun. 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.
managed_cleanup_dryrun 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 →