vm_start

THE RISK

High Risk

Why vm_start needs a policy

Starting a VM is an Execute action—it runs an external operation with side effects that persist beyond the tool call. While not immediately destructive or financial, a VM start can incur compute costs and consume resources, and an agent could launch many VMs causing significant infrastructure impact.

From the tool's definition Tool name 'vm_start' and description 'Start a stopped VM instance' indicate execution of an external operation (VM startup) whose effects depend on arguments (which VM to start).

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

POLICY

How to control vm_start

PolicyLayer is an MCP gateway — it sits between your AI agents and tmux-claude MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for vm_start:

policy.json

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

vm_start 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.

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

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More tmux-claude MCP Server tools

Destructive terminate Terminate a Claude instance and optionally its children Destructive vm_terminate Terminate a VM instance (permanent destruction) Execute executeParallel Execute multiple tasks in parallel using Specialist instances (Manager only) Execute restart Restart a dead instance using --continue flag Execute vm_stop Stop a running VM instance Execute distributeWork Distribute tasks across multiple Managers (Executive only) Execute enhancedSend Send a message with queuing and guaranteed delivery Execute merge_manager_work Coordinate merge of manager work back to main branch (Executive only)

All 26 tmux-claude MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in tmux-claude MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-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.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about vm_start

What does the vm_start tool do? +

Start a stopped VM instance. It is categorised as a Execute tool in the tmux-claude MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on vm_start? +

Register the tmux-claude MCP Server MCP server in PolicyLayer and add a rule for vm_start: 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 tmux-claude MCP Server. Nothing to install.

What risk level is vm_start? +

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

Can I rate-limit vm_start? +

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

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

vm_start is provided by the tmux-claude MCP Server MCP server (michael-abdo/tmux-claude-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every tmux-claude MCP Server tool call.

Start from tmux-claude MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →