// SCAN REPORT

Ai Mcp Terminal

26 tools. 17 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

17 can modify or destroy data

9 read-only

26 tools total

Community server · catalogue entry verified 29/06/2026

How to control Ai Mcp Terminal ↓

TOOL MAP

What Ai Mcp Terminal exposes to your agents

Read (9) Write / Execute (16) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Ai Mcp Terminal tools

Destructive · High kill_session This tool destroys a terminal session permanently without recovery options. Execute · High batch_send_keys Given the server context (multi-threaded terminal management enabling async command execution) and the tool name 'batch_send_keys', this tool almost certainly sends keyboard input to one or more terminal sessions in batc Execute · Critical execute_batch This tool executes arbitrary commands in batch across multiple terminal sessions. Execute · Critical execute_command This tool executes arbitrary commands in a terminal environment.

17 of Ai Mcp Terminal's 26 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Ai Mcp Terminal

PolicyLayer is an MCP gateway — it sits between your AI agents and Ai Mcp Terminal, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "kill_session": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Cap read operations

{
  "detect_interactions": {
    "limits": [
      {
        "counter": "detect_interactions_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Ai Mcp Terminal — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON AI MCP TERMINAL →

Instant setup, no code required.

FULL CATALOGUE

All 26 Ai Mcp Terminal tools

DESTRUCTIVE 1 tools

Destructive kill_session Delete entire terminal session (including terminal itself). WARNING: This deletes the terminal, if you only wa

EXECUTE 16 tools

Execute batch_send_keys batch_send_keys Execute broadcast_command broadcast_command Execute check_completion check_completion Execute create_batch create_batch Execute create_session create_session Execute execute_batch execute_batch Execute execute_command execute_command Execute execute_sequence execute_sequence Execute execute_with_retry execute_with_retry Execute execute_workflow execute_workflow Execute interrupt_batch interrupt_batch Execute interrupt_command v2.0.3: Interrupt current command but keep terminal (like Ctrl+C). Terminal becomes idle state, can continue e Execute send_input v2.0: Send input to terminal, for responding to interactive commands (like npm init). When detect_interactions Execute send_keys v1.0.2: Send any key or text to terminal. Supports all keyboard keys: letters, numbers, symbols, function keys Execute send_text v1.0.2: Quick send text to terminal (convenience method of send_keys). Sends string directly, not parsed as ke Execute wait_until_complete wait_until_complete

READ 9 tools

Read detect_interactions v2.0: Detect which terminals are waiting for user input. Identifies common prompt patterns (package name:, ver Read get_all_sessions Get list and status of all terminal sessions Read get_batch_output get_batch_output Read get_live_output v1.0.2: Get terminal Read get_output get_output Read get_session_status get_session_status Read get_stats Get system statistics information, including memory usage, terminal count, etc Read get_terminal_states v2.0: Get detailed states of all terminals, core tool for AI task scheduling. Returns each terminal Read kill_batch kill_batch

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Ai Mcp Terminal

Can an AI agent delete data through the Ai Mcp Terminal MCP server? +

Yes. The Ai Mcp Terminal server exposes 1 destructive tools including kill_session. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How many tools does the Ai Mcp Terminal MCP server expose? +

26 tools across 4 categories: Destructive, Execute, Read, Write. 9 are read-only. 17 can modify, create, or delete data.

How do I enforce a policy on Ai Mcp Terminal? +

Register the Ai Mcp Terminal MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Ai Mcp Terminal tool call.

Deterministic rules across all 26 Ai Mcp Terminal tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AI MCP TERMINAL →

Instant setup, no code required.

26 Ai Mcp Terminal tools catalogued and risk-classified — across an index of 43,000+ MCP servers.