key_type · Mcp Remotetouch MCP: Risk & Policy

WHAT IT DOES

What key_type does on Mcp Remotetouch

AI agents invoke key_type to trigger actions in Mcp Remotetouch. 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 key_type needs a policy

This tool simulates keyboard input on a remote device, which is an external operation with effects entirely dependent on the arguments passed. An AI agent could misuse it to type arbitrary text into any focused application (e.g., terminal commands, passwords, destructive inputs), giving it high blast radius. It falls under Execute as it triggers external operations on a remote system.

From the tool's definition 'Type a string of text on the remote device by simulating individual key presses' — executes input simulation on a remote Linux device over SSH

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

key_type Rate-limited

key_type 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": {
    "key_type": {
      "limits": [
        {
          "counter": "key_type_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 Mcp Remotetouch, so you can run agents against it safely.

FAQ

Questions about key_type

What does the key_type tool do? +

Type a string of text on the remote device by simulating individual key presses. Requires /dev/uinput access. It is categorised as a Execute tool in the Mcp Remotetouch MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on key_type? +

Register the Mcp Remotetouch MCP server in PolicyLayer and add a rule for key_type: 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 Remotetouch. Nothing to install.

What risk level is key_type? +

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

Can I rate-limit key_type? +

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

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

key_type is provided by the Mcp Remotetouch MCP server (signal-slot/mcp-remotetouch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.