Execute arbitrary C# code inside the Unity Editor. The code runs in the editor context with access to all Unity APIs. Useful for one-off operations, queries, and automation. Return values are serialized to JSON.
AI agents invoke unity_execute_code to trigger actions in Unity MCP Server. 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.
This tool permits execution of arbitrary code within a running application context with full API access. An AI agent could use this to execute malicious scripts, delete files, modify projects, exfiltrate data, or compromise the development environment. The 'arbitrary' qualifier and unrestricted API access elevate this to critical severity.
From the tool's definition Tool explicitly allows 'Execute arbitrary C# code inside the Unity Editor' with 'access to all Unity APIs'. The description directly indicates code execution capability without restrictions on what that code can do.
Documented attack patterns abuse exactly the kind of access unity_execute_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Unity MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for unity_execute_code:
{
"version": "1",
"default": "deny",
"tools": {
"unity_execute_code": {
"limits": [
{
"counter": "unity_execute_code_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}unity_execute_code 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.
Free to start. No card required.
Execute arbitrary C# code inside the Unity Editor. The code runs in the editor context with access to all Unity APIs. Useful for one-off operations, queries, and automation. Return values are serialized to JSON. It is categorised as a Execute tool in the Unity MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Unity MCP Server MCP server in PolicyLayer and add a rule for unity_execute_code: 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 Server. Nothing to install.
unity_execute_code is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the unity_execute_code 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.
Set action: deny in the PolicyLayer policy for unity_execute_code. 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.
unity_execute_code is provided by the Unity MCP Server MCP server (anklebreaker-studio/unity-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Unity MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
324 Unity MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.