execute_csharp · Unity MCP: Risk & Policy

WHAT IT DOES

What execute_csharp does on Unity MCP

AI agents invoke execute_csharp to trigger actions in Unity MCP. 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 execute_csharp needs a policy

This tool executes arbitrary code (C#) in the Unity Editor environment with unrestricted access to engine and editor APIs. While it could theoretically be used for reads, writes, or destructive operations depending on the code passed to it, the primary capability is code execution with side effects that depend entirely on the AI's input. The 'full access' and 'ANY operation' language indicates no guardrails.

From the tool's definition Execute arbitrary C# code in Unity Editor context with full access to UnityEngine and UnityEditor APIs. The description explicitly states it 'enables you to perform ANY Unity operation' without constraints.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_csharp Rate-limited

execute_csharp 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": {
    "execute_csharp": {
      "limits": [
        {
          "counter": "execute_csharp_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 Unity MCP, so you can run agents against it safely.

FAQ

Questions about execute_csharp

What does the execute_csharp tool do? +

Execute arbitrary C# code in Unity Editor context with full access to UnityEngine and UnityEditor APIs. This is the most powerful tool - it enables you to perform ANY Unity operation without predefined tools. Examples: - Select objects: Selection.activeGameObject = GameObject.Find(. It is categorised as a Execute tool in the Unity MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_csharp? +

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

What risk level is execute_csharp? +

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

Can I rate-limit execute_csharp? +

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

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

execute_csharp is provided by the Unity MCP server (muammar-yacoob/unity-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.