kill_process

THE RISK

Critical Risk

Why kill_process needs a policy

Killing a process is an irreversible action — the process is terminated immediately and any unsaved state is lost. This cannot be undone, placing it firmly in the Destructive category. The description itself warns 'Use with caution', reinforcing the high blast radius: an AI agent misusing this could terminate critical system processes, services, or user applications, causing data loss or system instability.

From the tool's definition "Terminate a running process by PID. Use with caution as this will"

Documented attack patterns abuse exactly the kind of access kill_process gives an agent:

POLICY

How to control kill_process

PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Desktop Commander MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for kill_process:

policy.json

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

kill_process disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register Claude Desktop Commander MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Claude Desktop Commander MCP tools

Destructive force_terminate Force terminate a running terminal session. Execute unblock_command Remove a command from the blacklist. Once unblocked, the command can be executed normally. Execute execute_command Execute a terminal command with timeout. Command will continue running in background if it Write block_command Add a command to the blacklist. Once blocked, the command cannot be executed until unblock Write create_directory Create a new directory or ensure a directory exists. Can create multiple Write edit_block Apply surgical text replacements to files. Best for small changes (<20% of file size). Write move_file Move or rename files and directories. Can move files between directories Write write_file Completely replace file contents. Best for large changes (>20% of file) or when edit_block

All 19 Claude Desktop Commander MCP tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in Claude Desktop Commander MCP → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about kill_process

What does the kill_process tool do? +

Terminate a running process by PID. Use with caution as this will. It is categorised as a Destructive tool in the Claude Desktop Commander MCP 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 kill_process? +

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

What risk level is kill_process? +

kill_process 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 kill_process? +

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

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

kill_process is provided by the Claude Desktop Commander MCP server (strawhatai/claude-dev-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Claude Desktop Commander MCP tool call.

Start from Claude Desktop Commander MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →