terminal_send_input

THE RISK

High Risk

Why terminal_send_input needs a policy

This tool sends arbitrary input to live terminal sessions running on a Kali Linux penetration testing platform. It can control any interactive program or shell, effectively allowing execution of arbitrary commands. In the context of a server with 500+ offensive security tools, misuse could trigger attacks, data exfiltration, or system compromise.

From the tool's definition 'Send raw input to a terminal session (for interactive programs)' on a server exposing 'over 500 Kali Linux security tools' for 'automated penetration testing'

Documented attack patterns abuse exactly the kind of access terminal_send_input gives an agent:

POLICY

How to control terminal_send_input

PolicyLayer is an MCP gateway — it sits between your AI agents and Kali-Mcp-Toolkit, and nothing reaches the server without passing your rules. This is the rule we recommend for terminal_send_input:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "terminal_send_input": {
      "limits": [
        {
          "counter": "terminal_send_input_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

terminal_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.

Create a free account and register Kali-Mcp-Toolkit — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Kali-Mcp-Toolkit tools

Destructive terminal_kill Destroy a terminal session and free resources. Execute code_execute Execute a script/program from the workspace. Execute shell_connection_exec Execute a command on a reverse-shell connection and return output. Execute shell_listener_start Start a reverse-shell listener (requires admin scope, must be enabled in config). Execute shell_listener_stop Stop a reverse-shell listener. Execute terminal_exec Execute a command in an existing terminal session. Execute exec_tool exec_tool Execute code_install_deps Install packages (requires admin scope, must be enabled in config).

All 20 Kali-Mcp-Toolkit tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Kali-Mcp-Toolkit → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about terminal_send_input

What does the terminal_send_input tool do? +

Send raw input to a terminal session (for interactive programs). It is categorised as a Execute tool in the Kali-Mcp-Toolkit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on terminal_send_input? +

Register the Kali-Mcp-Toolkit MCP server in PolicyLayer and add a rule for terminal_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 Kali-Mcp-Toolkit. Nothing to install.

What risk level is terminal_send_input? +

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

Can I rate-limit terminal_send_input? +

Yes. Add a rate_limit block to the terminal_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 terminal_send_input completely? +

Set action: deny in the PolicyLayer policy for terminal_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 terminal_send_input? +

terminal_send_input is provided by the Kali-Mcp-Toolkit MCP server (trymonoly/kali-mcp-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Kali-Mcp-Toolkit tool call.

Start from Kali-Mcp-Toolkit, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →