shell_stop_process · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What shell_stop_process does on LocalAnt

AI agents invoke shell_stop_process to trigger actions in LocalAnt. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why shell_stop_process needs a policy

Stopping a process executes a system-level action with externally visible consequences (application/service shutdown). While not destructive in the sense of permanent data loss, process termination affects system state in ways that depend on which process is targeted and can disrupt services or workflows.

From the tool's definition The tool description states it 'Stop[s] a tracked process', which terminates a running process on the system. Process termination is an external operation that triggers immediate effects on system state and cannot be easily reverted in all contexts.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

shell_stop_process Rate-limited

shell_stop_process stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "shell_stop_process": {
      "limits": [
        {
          "counter": "shell_stop_process_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches LocalAnt, so you can run agents against it safely.

FAQ

Questions about shell_stop_process

What does the shell_stop_process tool do? +

Stop a tracked process. It is categorised as a Execute tool in the LocalAnt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on shell_stop_process? +

Register the LocalAnt MCP server in PolicyLayer and add a rule for shell_stop_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 LocalAnt. Nothing to install.

What risk level is shell_stop_process? +

shell_stop_process is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit shell_stop_process? +

Yes. Add a rate_limit block to the shell_stop_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 shell_stop_process completely? +

Set action: deny in the PolicyLayer policy for shell_stop_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 shell_stop_process? +

shell_stop_process is provided by the LocalAnt MCP server (yuga-hashimoto/localant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.