invoke_button

SERVERSbox SOURCEsbox-mcp-server

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/sbox/invoke-button.md

WHAT IT DOES

What invoke_button does on Sbox

AI agents invoke invoke_button to trigger actions in Sbox. 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 invoke_button is rated High

The tool enables execution of arbitrary public methods on game engine components. While the description is incomplete (ends with "(e.g."), the core capability is clearly method invocation, which constitutes code execution. The ability to call ANY public method (not just [Button]-attributed ones) means an AI agent could trigger game state modifications, physics updates, asset loading, or other side effects.

From the tool's definition "Call a public method on a component" and "Calls ANY public method" — this tool invokes arbitrary public methods on game engine components, which can trigger code execution with side effects depending on the method implementation.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs invoke_button safely

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

invoke_button Rate-limited

invoke_button 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": {
    "invoke_button": {
      "limits": [
        {
          "counter": "invoke_button_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 Sbox, apply this rule, and every invoke_button call is checked against it from then on.

FAQ

Questions about invoke_button

What does the invoke_button tool do? +

Call a public method on a component. Matching is tried in order: (1) a [Button] attribute label, (2) the exact method NAME, (3) case-insensitive name with spaces stripped. Calls ANY public method, not only [Button]-attributed ones (e.g. It is categorised as a Execute tool in the Sbox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on invoke_button? +

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

What risk level is invoke_button? +

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

Can I rate-limit invoke_button? +

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

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

invoke_button is provided by the Sbox MCP server (sbox-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Sbox, and thousands of servers like it.

This server

All 207 Sbox tools → High-risk tools on this server →

Across the catalogue

qt_invoke_slot on Qt → All high-risk MCP tools → The MCP Attack Database →

Guides

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