clean-process-ended
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CPE_HOST_PROFILE | No | Host profile to use. Options: codex, claude_code, gemini_cli, qwen_code, generic_mcp_host. | generic_mcp_host |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| process_scope_reportA | Scan local processes, reconcile them with this session ledger, and report agent/MCP process ownership without terminating anything. |
| process_cleanup_candidatesA | Return detailed candidates grouped by ownership. This is audit-only and never terminates processes. |
| process_cleanupA | 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. |
| janitor_discoveryA | Return non-destructive machine-readable guidance for when agents should use clean-process-ended. It does not scan processes and never terminates anything. |
| session_close_checkA | Run a compact non-destructive close-task check with one process snapshot and a dry-run cleanup plan. It never returns a live confirm token and never terminates processes. |
| process_explainB | Explain a single PID with ownership evidence, host/tool profiles, reasons, blockers, and cleanup eligibility. It never terminates processes. |
| profile_listC | List configured host and tool profiles used as weak signals for process classification. |
| config_explainA | Explain effective config, config paths, data directory, and safety defaults without exposing command line secrets. |
| session_statusA | Show this MCP instance identity, session epoch, baseline, and watcher status. |
| ledger_readC | Read the local process ledger summary, recent snapshot metadata, and recent cleanup events. |
| watcher_statusA | Show the status of the embedded watcher that takes periodic non-destructive snapshots while this MCP server is running. |
| watcher_reconcile_nowB | Force a watcher reconciliation snapshot now. It updates the ledger and does not terminate anything. |
| audit_bundleB | Generate a single non-destructive audit payload with config, session, report, candidates, dry-run metrics and safety metadata. |
| policy_explainB | Explain cleanup and auto-cleanup policy gates for one PID. It never terminates processes. |
| stale_session_reportB | Report previous sessions from this installation that appear stale. This is report-only. |
| resource_impact_reportC | Summarize CPU/RSS impact, top blockers, and report partitions for related processes. |
| auto_cleanup_statusA | Show experimental auto-cleanup policy status and gates. Auto-cleanup is disabled by default. |
| auto_cleanup_dryrunC | Plan experimental auto-cleanup without terminating anything, even when auto-cleanup is disabled. |
| managed_process_listC | List processes launched explicitly through cpe-run lifecycle management. This is report-only. |
| managed_process_explainB | Explain one cpe-run managed process record by managedProcessId. It never terminates processes. |
| managed_reconcileA | Reconcile explicit cpe-run managed process records against the current process table. It never terminates processes. |
| managed_lifecycle_reportA | Report lifecycle state for cpe-run managed processes: running, missing, exited, expired or PID-reuse mismatch. |
| managed_cleanup_dryrunA | Plan cleanup for managed processes only. This is dry-run only and never terminates processes. |
| managed_stale_reportB | Report stale managed process records. This is report-only evidence. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MarceloCaporale/clean-process-ended'
If you have feedback or need assistance with the MCP directory API, please join our Discord server