user_keyboard_input · Melo MCP: Risk & Policy

WHAT IT DOES

What user_keyboard_input does on Melo

AI agents invoke user_keyboard_input 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 user_keyboard_input needs a policy

This tool simulates keyboard input during an active playtest session, triggering external operations (keypress events) within the Roblox Studio environment. The effects depend on which key is pressed and the current game state.

From the tool's definition Simulate keyboard presses during a playtest

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

user_keyboard_input Rate-limited

user_keyboard_input 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": {
    "user_keyboard_input": {
      "limits": [
        {
          "counter": "user_keyboard_input_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 user_keyboard_input

What does the user_keyboard_input tool do? +

Simulate keyboard presses during a playtest. Args: - key (string): Key to press (e.g. 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 user_keyboard_input? +

Register the Melo MCP server in PolicyLayer and add a rule for user_keyboard_input: 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 user_keyboard_input? +

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

Can I rate-limit user_keyboard_input? +

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

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

user_keyboard_input 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.