process_cleanup · Clean Process Ended MCP: Risk & Policy

WHAT IT DOES

What process_cleanup does on Clean Process Ended

AI agents invoke process_cleanup to trigger actions in Clean Process Ended. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why process_cleanup needs a policy

The tool's core function is to terminate subprocesses ("termination", "cleanup"). Although currently constrained to dry-run mode with safety gates blocking actual execution (dry_run=false), the semantic intent and capability is Execute: triggering external process termination whose effects depend on which processes are selected.

From the tool's definition Dry-run selected owned_current_session candidates. In v0.7.x public CLI/MCP, real termination remains non-operable because evidence inputs are not exposed; dry_run=false stays blocked by safety gates. Agents must not call dry_run=false autonomously.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

process_cleanup Rate-limited

process_cleanup stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "process_cleanup": {
      "limits": [
        {
          "counter": "process_cleanup_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Clean Process Ended, so you can run agents against it safely.

FAQ

Questions about process_cleanup

What does the process_cleanup tool do? +

Dry-run selected owned_current_session candidates. In v0.7.x public CLI/MCP, real termination remains non-operable because evidence inputs are not exposed; dry_run=false stays blocked by safety gates. Agents must not call dry_run=false autonomously. It is categorised as a Execute tool in the Clean Process Ended MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on process_cleanup? +

Register the Clean Process Ended MCP server in PolicyLayer and add a rule for process_cleanup: 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.

What risk level is process_cleanup? +

process_cleanup is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit process_cleanup? +

Yes. Add a rate_limit block to the process_cleanup 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.

How do I block process_cleanup completely? +

Set action: deny in the PolicyLayer policy for process_cleanup. 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.

What MCP server provides process_cleanup? +

process_cleanup 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.