kill_process
Terminate or kill a process by PID.
This record as markdown: /tools/19miha99-system-monitor-mcp/kill-process.md
What kill_process does on Desktop Commander MCP Server
AI agents call kill_process to permanently remove resources in Desktop Commander MCP Server, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why kill_process is rated Critical
Killing a process is an irreversible action: any unsaved data in that process is lost, and critical system or application processes being killed can cause crashes or service outages. This matches the Destructive category due to its non-undoable nature and high blast radius if misused by an AI agent.
From the tool's definition "Terminate or kill a process by PID" — forcibly ends a running process, which is irreversible and may cause data loss or system instability.
Attacks that exploit this kind of access
The rule that runs kill_process safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Desktop Commander MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For kill_process, this is the rule to start with:
kill_process is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Desktop Commander MCP Server, apply this rule, and every kill_process call is checked against it from then on.
Questions about kill_process
Terminate or kill a process by PID. It is categorised as a Destructive tool in the Desktop Commander MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Desktop Commander MCP Server 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 Desktop Commander MCP Server. Nothing to install.
kill_process is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
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.
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.
kill_process is provided by the Desktop Commander MCP Server MCP server (19miha99/system-monitor-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Desktop Commander MCP Server, and thousands of servers like it.
Across the catalogue