control_execution · Smart Xdebug MCP: Risk & Policy

WHAT IT DOES

What control_execution does on Smart Xdebug

AI agents invoke control_execution to trigger actions in Smart Xdebug. 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 control_execution needs a policy

Controlling a debugger involves directing execution of a running PHP process — stepping through code, continuing execution, or pausing it. This is an Execute-category action because it triggers external operations (runtime PHP execution) whose effects depend on arguments.

From the tool's definition 'Controls the debugger' — the tool controls execution flow of a PHP XDebug debug session (e.g., step, continue, pause), which triggers external runtime operations in the PHP process.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

control_execution Rate-limited

control_execution 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": {
    "control_execution": {
      "limits": [
        {
          "counter": "control_execution_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 Smart Xdebug, so you can run agents against it safely.

FAQ

Questions about control_execution

What does the control_execution tool do? +

Controls the debugger. It is categorised as a Execute tool in the Smart Xdebug MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on control_execution? +

Register the Smart Xdebug MCP server in PolicyLayer and add a rule for control_execution: 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 Smart Xdebug. Nothing to install.

What risk level is control_execution? +

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

Can I rate-limit control_execution? +

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

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

control_execution is provided by the Smart Xdebug MCP server (wallter/smart-xdebug-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.