send_input · Zmachine MCP: Risk & Policy

WHAT IT DOES

What send_input does on Zmachine

AI agents invoke send_input to trigger actions in Zmachine. 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 send_input needs a policy

Sending input to a Z-Machine session executes interpreter commands that mutate game state (inventory, world state, progression). While the blast radius is contained to a game session, it is an active execution of commands with state-changing side effects rather than a simple read. It is not destructive in the irreversible real-world sense, but it does drive external process execution.

From the tool's definition "Send a text command to an active game session and get the response" — triggers execution of commands within the Z-Machine interpreter, producing side effects within the game state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_input Rate-limited

send_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": {
    "send_input": {
      "limits": [
        {
          "counter": "send_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 Zmachine, so you can run agents against it safely.

FAQ

Questions about send_input

What does the send_input tool do? +

Send a text command to an active game session and get the response. It is categorised as a Execute tool in the Zmachine MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on send_input? +

Register the Zmachine MCP server in PolicyLayer and add a rule for send_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 Zmachine. Nothing to install.

What risk level is send_input? +

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

Can I rate-limit send_input? +

Yes. Add a rate_limit block to the send_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 send_input completely? +

Set action: deny in the PolicyLayer policy for send_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 send_input? +

send_input is provided by the Zmachine MCP server (jonathan-meyer/zmachine-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.