godot_exec

Executa codigo GDScript DENTRO do jogo rodando.

SERVERMcp Godot Desenvolvimento SOURCEjoabcostamd/mcp-godot-desenvolvimento

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/mcp-godot-desenvolvimento/godot-exec.md

WHAT IT DOES

What godot_exec does on Mcp Godot Desenvolvimento

AI agents invoke godot_exec to trigger actions in Mcp Godot Desenvolvimento. 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.

RISK

Why godot_exec is rated High

This tool runs arbitrary GDScript code inside a live Godot game process. An AI agent could use it to execute any logic, modify game state, access the filesystem, make network calls, or cause crashes. The blast radius is critical because it provides unrestricted code execution within a running process, with effects entirely dependent on the code passed as argument.

From the tool's definition 'Executa codigo GDScript DENTRO do jogo rodando' — executes GDScript code inside a running game instance

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs godot_exec safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Godot Desenvolvimento, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For godot_exec, this is the rule to start with:

godot_exec Rate-limited

godot_exec 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": {
    "godot_exec": {
      "limits": [
        {
          "counter": "godot_exec_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Godot Desenvolvimento, apply this rule, and every godot_exec call is checked against it from then on.

FAQ

Questions about godot_exec

What does the godot_exec tool do? +

Executa codigo GDScript DENTRO do jogo rodando. It is categorised as a Execute tool in the Mcp Godot Desenvolvimento MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on godot_exec? +

Register the Mcp Godot Desenvolvimento MCP server in PolicyLayer and add a rule for godot_exec: 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 Mcp Godot Desenvolvimento. Nothing to install.

What risk level is godot_exec? +

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

Can I rate-limit godot_exec? +

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

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

godot_exec is provided by the Mcp Godot Desenvolvimento MCP server (joabcostamd/mcp-godot-desenvolvimento). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Mcp Godot Desenvolvimento, and thousands of servers like it.

This server

All 292 Mcp Godot Desenvolvimento tools → High-risk tools on this server →

Across the catalogue

bash_exec on 0sec → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →