Iterm MCP Server

A Model Context Protocol server that provides access to the currently active tab of iTerm

Local serverstdio

What is the Iterm MCP server?

Iterm MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. A Model Context Protocol server that provides access to the currently active tab of iTerm.

What you get

On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

What the assistant can call

Once Iterm is connected, these are the calls the assistant has available:

  • write_to_terminal — Writes to the active iTerm terminal, often used to run a command. Returns the number of lines of output produced by the command
  • read_terminal_output — Reads the requested number of lines from the active iTerm terminal
  • send_control_character — Sends a control character to the active iTerm terminal
  • Features — The Features tool exposed by this server
  • Tools — The Tools tool exposed by this server
  • Requirements — The Requirements tool exposed by this server
  • Debugging — Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP

Setting it up

The server ships on npm as @smithery/cli, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Configuration and credentials

  • iTerm2 must be running * Node version 18 or greater

Choosing this one

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Iterm's toolset — write_to_terminal, read_terminal_output, send_control_character and 4 more — is a fair guide to whether it matches your workflow. It is maintained by deathmonger5000; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the iterm mcp server does with a few real requests.

Available tools

ToolWhat it does
write_to_terminalWrites to the active iTerm terminal, often used to run a command. Returns the number of lines of output produced by the command.
read_terminal_outputReads the requested number of lines from the active iTerm terminal.
send_control_characterSends a control character to the active iTerm terminal.
FeaturesThe Features tool exposed by this server.
ToolsThe Tools tool exposed by this server.
RequirementsThe Requirements tool exposed by this server.
DebuggingSince MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector), which is available as a package script:

How to install the Iterm MCP server

{
  "mcpServers": {
    "iterm-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "iterm-mcp"
      ]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • iTerm2 must be running * Node version 18 or greater

Example prompts to try

  • Use Iterm to write to terminal.
  • Use Iterm to read terminal output.
  • Use Iterm to send control character.

Frequently asked questions

It connects Iterm to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (write_to_terminal, read_terminal_output, send_control_character, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Iterm directly.