run_custom_command · Reactotron MCP: Risk & Policy

WHAT IT DOES

What run_custom_command does on Reactotron

AI agents invoke run_custom_command to trigger actions in Reactotron. 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 run_custom_command needs a policy

run_custom_command triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_custom_command Rate-limited

run_custom_command 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": {
    "run_custom_command": {
      "limits": [
        {
          "counter": "run_custom_command_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 Reactotron, so you can run agents against it safely.

FAQ

Questions about run_custom_command

What does the run_custom_command tool do? +

Trigger a custom command registered by the app in Reactotron. Call with no. It is categorised as a Execute tool in the Reactotron MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_custom_command? +

Register the Reactotron MCP server in PolicyLayer and add a rule for run_custom_command: 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 Reactotron. Nothing to install.

What risk level is run_custom_command? +

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

Can I rate-limit run_custom_command? +

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

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

run_custom_command is provided by the Reactotron MCP server (steve228uk/reactotron-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.