// SCAN REPORT

Iterm2

18 tools. 12 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

12 can modify or destroy data

6 read-only

18 tools total

Community server · catalogue entry verified 03/07/2026

How to control Iterm2 ↓

TOOL MAP

What Iterm2 exposes to your agents

Read (6) Write / Execute (11) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Iterm2 tools

Destructive · High clear_buffer Clearing the scrollback buffer is an irreversible action — once the terminal history is erased, it cannot be recovered. Execute · Critical run_command This tool executes arbitrary shell commands in iTerm2 sessions. Execute · Medium create_tab Creating a tab in a terminal emulator initiates a new terminal session, which is an external operation with side effects. Execute · Low focus_session Focusing a session is an external operation that manipulates the state of the iTerm2 application (bringing a window/tab/pane to the foreground).

12 of Iterm2's 18 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Iterm2

PolicyLayer is an MCP gateway — it sits between your AI agents and Iterm2, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

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

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

Rate limit write operations

{
  "close_session": {
    "limits": [
      {
        "counter": "close_session_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_active_session": {
    "limits": [
      {
        "counter": "get_active_session_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 Iterm2 — 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 ITERM2 →

Instant setup, no code required.

FULL CATALOGUE

All 18 Iterm2 tools

DESTRUCTIVE 1 tools

Destructive clear_buffer Clear both the visible screen and the scrollback buffer.

EXECUTE 7 tools

Execute create_tab Create a new tab in a window. Execute focus_session Bring a session to the foreground. Execute run_command run_command Execute send_control_character send_control_character Execute send_escape_sequence send_escape_sequence Execute split_pane split_pane Execute write_to_terminal write_to_terminal

WRITE 4 tools

Write close_session Close a specific session. Write create_window Create a new iTerm2 window. Write set_badge set_badge Write set_session_name Set the title/name of an iTerm2 session.

READ 6 tools

Read get_active_session Return the ID and name of the currently focused iTerm2 session. Read get_cursor_position Return the cursor coordinates x, y within the visible screen. Read get_variable get_variable Read list_profiles List all iTerm2 profiles with their names and GUIDs. Read list_sessions List all iTerm2 windows, tabs, and sessions. Read read_screen Read the visible contents of an iTerm2 session as plain text.

EXPLORE

Related servers

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

FAQ

Questions about Iterm2

Can an AI agent delete data through the Iterm2 MCP server? +

Yes. The Iterm2 server exposes 1 destructive tools including clear_buffer. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Iterm2? +

The Iterm2 server has 4 write tools including close_session, create_window, set_badge. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Iterm2.

How many tools does the Iterm2 MCP server expose? +

18 tools across 4 categories: Destructive, Execute, Read, Write. 6 are read-only. 12 can modify, create, or delete data.

How do I enforce a policy on Iterm2? +

Register the Iterm2 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 Iterm2 tool call.

Deterministic rules across all 18 Iterm2 tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ITERM2 →

Instant setup, no code required.

18 Iterm2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.