// SCAN REPORT

Clean Process Ended

24 tools. 2 can modify or destroy data without limits.

2 write tools that can modify data. Rate limits recommended.

Last updated: 29 Jun 2026

2 can modify or destroy data

22 read-only

24 tools total

Community server · catalogue entry verified 29/06/2026

How to control Clean Process Ended ↓

TOOL MAP

What Clean Process Ended exposes to your agents

Read (22) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Clean Process Ended tools

Execute · High process_cleanup The tool's core function is to terminate subprocesses ("termination", "cleanup"). Write · Medium watcher_reconcile_now The tool triggers an immediate watcher reconciliation that updates the ledger, which is a write operation (modifying stored state).

2 of Clean Process Ended's 24 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Clean Process Ended

PolicyLayer is an MCP gateway — it sits between your AI agents and Clean Process Ended, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "watcher_reconcile_now": {
    "limits": [
      {
        "counter": "watcher_reconcile_now_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "audit_bundle": {
    "limits": [
      {
        "counter": "audit_bundle_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Clean Process Ended — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON CLEAN PROCESS ENDED →

Instant setup, no code required.

FULL CATALOGUE

All 24 Clean Process Ended tools

EXECUTE 1 tools

Execute process_cleanup Dry-run selected owned_current_session candidates. In v0.7.x public CLI/MCP, real termination remains non-oper

WRITE 1 tools

Write watcher_reconcile_now Force a watcher reconciliation snapshot now. It updates the ledger and does not terminate anything.

READ 22 tools

Read audit_bundle Generate a single non-destructive audit payload with config, session, report, candidates, dry-run metrics and Read auto_cleanup_dryrun Plan experimental auto-cleanup without terminating anything, even when auto-cleanup is disabled. Read auto_cleanup_status Show experimental auto-cleanup policy status and gates. Auto-cleanup is disabled by default. Read config_explain Explain effective config, config paths, data directory, and safety defaults without exposing command line secr Read janitor_discovery Return non-destructive machine-readable guidance for when agents should use clean-process-ended. It does not s Read ledger_read Read the local process ledger summary, recent snapshot metadata, and recent cleanup events. Read managed_cleanup_dryrun Plan cleanup for managed processes only. This is dry-run only and never terminates processes. Read managed_lifecycle_report Report lifecycle state for cpe-run managed processes: running, missing, exited, expired or PID-reuse mismatch. Read managed_process_explain Explain one cpe-run managed process record by managedProcessId. It never terminates processes. Read managed_process_list List processes launched explicitly through cpe-run lifecycle management. This is report-only. Read managed_reconcile Reconcile explicit cpe-run managed process records against the current process table. It never terminates proc Read managed_stale_report Report stale managed process records. This is report-only evidence. Read policy_explain Explain cleanup and auto-cleanup policy gates for one PID. It never terminates processes. Read process_cleanup_candidates Return detailed candidates grouped by ownership. This is audit-only and never terminates processes. Read process_explain Explain a single PID with ownership evidence, host/tool profiles, reasons, blockers, and cleanup eligibility. Read process_scope_report Scan local processes, reconcile them with this session ledger, and report agent/MCP process ownership without Read profile_list List configured host and tool profiles used as weak signals for process classification. Read resource_impact_report Summarize CPU/RSS impact, top blockers, and report partitions for related processes. Read session_close_check Run a compact non-destructive close-task check with one process snapshot and a dry-run cleanup plan. It never Read session_status Show this MCP instance identity, session epoch, baseline, and watcher status. Read stale_session_report Report previous sessions from this installation that appear stale. This is report-only. Read watcher_status Show the status of the embedded watcher that takes periodic non-destructive snapshots while this MCP server is

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Clean Process Ended

How do I prevent bulk modifications through Clean Process Ended? +

The Clean Process Ended server has 1 write tools including watcher_reconcile_now. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Clean Process Ended.

How many tools does the Clean Process Ended MCP server expose? +

24 tools across 3 categories: Execute, Read, Write. 22 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Clean Process Ended? +

Register the Clean Process Ended MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Clean Process Ended tool call.

Deterministic rules across all 24 Clean Process Ended tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CLEAN PROCESS ENDED →

Instant setup, no code required.

24 Clean Process Ended tools catalogued and risk-classified — across an index of 43,000+ MCP servers.