send_input · Ai Mcp Terminal MCP: Risk & Policy

WHAT IT DOES

What send_input does on Ai Mcp Terminal

AI agents invoke send_input to trigger actions in Ai Mcp Terminal. 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

This tool sends input to a running terminal session, which directly drives interactive command execution. While it responds to prompts rather than initiating commands, it can influence arbitrary program behavior depending on context — e.g., responding to package manager prompts, shell inputs, or other interactive processes.

From the tool's definition Send input to terminal, for responding to interactive commands... AI uses this tool to send response

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 Ai Mcp Terminal, so you can run agents against it safely.

FAQ

Questions about send_input

What does the send_input tool do? +

v2.0: Send input to terminal, for responding to interactive commands (like npm init). When detect_interactions detects terminal waiting for input, AI uses this tool to send response. It is categorised as a Execute tool in the Ai Mcp Terminal 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 Ai Mcp Terminal 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 Ai Mcp Terminal. 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 Ai Mcp Terminal MCP server (kanniganfan/ai-mcp-terminal). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.