send_shell_input · Interactive Shell MCP: Risk & Policy

WHAT IT DOES

What send_shell_input does on Interactive Shell MCP

AI agents invoke send_shell_input to trigger actions in Interactive Shell MCP. 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_shell_input needs a policy

Sending input to a PTY shell session directly executes arbitrary shell commands or interacts with running programs. This is equivalent to typing into a terminal — it can run any command, modify or delete files, exfiltrate data, install malware, etc. The blast radius is critical because there are essentially no limits on what can be done through an open shell session.

From the tool's definition Writes input to the PTY... supports interactive programs... sequential command execution... full terminal emulation and PTY support

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_shell_input Rate-limited

send_shell_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_shell_input": {
      "limits": [
        {
          "counter": "send_shell_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 Interactive Shell MCP, so you can run agents against it safely.

FAQ

Questions about send_shell_input

What does the send_shell_input tool do? +

Writes input to the PTY. By default appends a carriage return. Use raw mode for interactive prompts (arrow keys, space to toggle, etc.). It is categorised as a Execute tool in the Interactive Shell MCP 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_shell_input? +

Register the Interactive Shell MCP server in PolicyLayer and add a rule for send_shell_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 Interactive Shell MCP. Nothing to install.

What risk level is send_shell_input? +

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

Can I rate-limit send_shell_input? +

Yes. Add a rate_limit block to the send_shell_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_shell_input completely? +

Set action: deny in the PolicyLayer policy for send_shell_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_shell_input? +

send_shell_input is provided by the Interactive Shell MCP server (lightos/interactive-shell-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.