execute · Cocos MCP: Risk & Policy

WHAT IT DOES

What execute does on Cocos MCP

AI agents invoke execute to trigger actions in Cocos 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 needs a policy

Execute tools that can run arbitrary code within editor/game engine contexts pose critical risk: agents could manipulate scenes destructively, corrupt assets, inject malicious logic, or compromise the entire project. Empty description lowers confidence slightly (0.95 vs 1.0) but the name and server purpose strongly indicate code execution capability.

From the tool's definition Tool name is 'execute' with empty description. Given the server context (Cocos Creator editor control bridge) and the presence of scene manipulation and asset management tools, an 'execute' tool most likely runs code, scripts, or commands within the Cocos…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute Rate-limited

execute 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": {
      "limits": [
        {
          "counter": "execute_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 Cocos MCP, so you can run agents against it safely.

FAQ

Questions about execute

What does the execute tool do? +

execute. It is categorised as a Execute tool in the Cocos 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? +

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

What risk level is execute? +

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

Can I rate-limit execute? +

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

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

execute is provided by the Cocos MCP server (wanghehacker/cocos-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.