force_terminate

Force terminate a running terminal session. ${CMD_PREFIX_DESCRIPTION}

SERVERDesktop Commander SOURCEwonderwhy-er/DesktopCommanderMCP

Critical RISK CLASS

Category Destructive

Parameters 00 required

Recommended Hiddensee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/desktop-commander/force-terminate.md

WHAT IT DOES

What force_terminate does on Desktop Commander

AI agents call force_terminate to permanently remove resources in Desktop Commander, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

RISK

Why force_terminate is rated Critical

Force terminating a terminal session is irreversible — any unsaved state, running processes, or in-progress operations are permanently lost. This cannot be undone, making it Destructive. The 'force' qualifier further implies bypassing normal shutdown procedures, increasing blast radius if misused by an AI agent.

From the tool's definition Force terminate a running terminal session

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs force_terminate safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Desktop Commander, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For force_terminate, this is the rule to start with:

force_terminate Hidden

force_terminate is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "force_terminate"
  ]
}

RESTRICT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Desktop Commander, apply this rule, and every force_terminate call is checked against it from then on.

FAQ

Questions about force_terminate

What does the force_terminate tool do? +

Force terminate a running terminal session. ${CMD_PREFIX_DESCRIPTION}. It is categorised as a Destructive tool in the Desktop Commander MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on force_terminate? +

Register the Desktop Commander MCP server in PolicyLayer and add a rule for force_terminate: 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 Desktop Commander. Nothing to install.

What risk level is force_terminate? +

force_terminate is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit force_terminate? +

Yes. Add a rate_limit block to the force_terminate 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 force_terminate completely? +

Set action: deny in the PolicyLayer policy for force_terminate. 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 force_terminate? +

force_terminate is provided by the Desktop Commander MCP server (wonderwhy-er/DesktopCommanderMCP). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Desktop Commander, and thousands of servers like it.

This server

All 11 Desktop Commander tools → Critical-risk tools on this server →

Across the catalogue

All critical-risk MCP tools → The MCP Attack Database →

Guides

Govern database agents →Blast radius →Tool call approval →