Start a playtest, run a script, then automatically stop. Returns all output. Useful for testing code changes without manual intervention. Args: - code (string): Luau code to execute during play - timeout (number, optional): Max seconds before auto-stop (default: 30) Returns: { output: string, err...
AI agents invoke run_script_in_play_mode 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.
This tool executes arbitrary Luau code within a Roblox Studio playtest environment. While not destructive by itself, code execution with access to game state and potentially game-altering APIs poses a high blast radius if an AI agent is compromised or misaligned. The playtest environment could modify game objects, trigger gameplay events, or cause unintended side effects.
From the tool's definition Tool description states 'run a script' and 'Luau code to execute during play'. The args accept arbitrary `code` string to be executed. This is explicit code execution with external effects (starting a playtest, running user-provided code, stopping playtest).
Attacks that exploit this kind of access
Start a playtest, run a script, then automatically stop. Returns all output. Useful for testing code changes without manual intervention. Args: - code (string): Luau code to execute during play - timeout (number, optional): Max seconds before auto-stop (default: 30) Returns: { output: string, errors: string[], duration: number }. 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.
Register the Melo MCP server in PolicyLayer and add a rule for run_script_in_play_mode: 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.
run_script_in_play_mode 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 run_script_in_play_mode 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 run_script_in_play_mode. 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.
run_script_in_play_mode 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →