start_playtest · Melo MCP: Risk & Policy

WHAT IT DOES

What start_playtest does on Melo

AI agents invoke start_playtest to trigger actions in Melo. 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 start_playtest needs a policy

The tool executes a game playtest session, which runs arbitrary Lua scripts and game code within Roblox Studio. This is not merely reading data (Read), nor reversibly creating/modifying configuration (Write). It actively triggers code execution in an external system (Roblox Studio) with effects that depend on the state of the project and its scripts.

From the tool's definition Tool description states 'Start a play session in Studio' and 'Begins capturing all print/warn/error output.' This triggers execution of a full playtest session within the Roblox development environment, which runs code and has side effects dependent on what…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_playtest Rate-limited

start_playtest 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": {
    "start_playtest": {
      "limits": [
        {
          "counter": "start_playtest_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 Melo, so you can run agents against it safely.

FAQ

Questions about start_playtest

What does the start_playtest tool do? +

Start a play session in Studio. Begins capturing all print/warn/error output. Use get_playtest_output to poll logs during the session, and stop_playtest to end it. Args: - mode (string, optional):. It is categorised as a Execute tool in the Melo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_playtest? +

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

What risk level is start_playtest? +

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

Can I rate-limit start_playtest? +

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

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

start_playtest is provided by the Melo MCP server (yannyhl/linkedsword-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.