The iTerm MCP Server enables a model to interact with and control your iTerm terminal session through these capabilities:
Run Commands: Write text or execute commands in the active terminal using write_to_terminal
Read Output: Read a specified number of lines from terminal output using read_terminal_output
Send Control Characters: Send signals like Control-C or Control-Z using send_control_character
REPL Interaction: Work with interactive programming environments or shell sessions
Efficient Integration: Focus on relevant output by reading only necessary lines, minimizing token usage
Task Management: Delegate and monitor tasks executed directly in your terminal environment
Provides access to the user's iTerm terminal session, allowing the model to read terminal output, write commands to the terminal, and send control characters for full terminal control.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@iTerm MCP Server list files in the current directory"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol server that provides access to your iTerm session.
Efficient Token Use: iterm-mcp gives the model the ability to inspect only the output that the model is interested in. The model typically only wants to see the last few lines of output even for long running commands.
Natural Integration: You share iTerm with the model. You can ask questions about what's on the screen, or delegate a task to the model and watch as it performs each step.
Full Terminal Control and REPL support: The model can start and interact with REPL's as well as send control characters like ctrl-c, ctrl-z, etc.
Easy on the Dependencies: iterm-mcp is built with minimal dependencies and is runnable via npx. It's designed to be easy to add to Claude Desktop and other MCP clients. It should just work.
The user is responsible for using the tool safely.
No built-in restrictions: iterm-mcp makes no attempt to evaluate the safety of commands that are executed.
Models can behave in unexpected ways. The user is expected to monitor activity and abort when appropriate.
For multi-step tasks, you may need to interrupt the model if it goes off track. Start with smaller, focused tasks until you're familiar with how the model behaves.
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.
iTerm2 must be running
Node version 18 or greater
Related MCP server: iTerm MCP Server
To use with Claude Desktop, add the server config:
On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"iterm-mcp": {
"command": "npx",
"args": [
"-y",
"iterm-mcp"
]
}
}
}To install iTerm for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install iterm-mcp --client claudeInstall dependencies:
yarn installBuild the server:
yarn run buildFor development with auto-rebuild:
yarn run watchSince MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
yarn run inspector
yarn debug <command>The Inspector will provide a URL to access debugging tools in your browser.
Reads the output from the active iTerm terminal
Inputs: linesOfOutput (required).
Sends a control character to the active iTerm terminal (e.g., Control-C, or special sequences like ']' for telnet escape)
Inputs: letter (required).
Writes text to the active iTerm terminal - often used to run a command in the terminal
Inputs: command (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool has a clearly distinct function: reading output, sending control characters, and writing text. No overlap in purpose.
All three tools follow a consistent verb_noun pattern in snake_case (read_terminal_output, send_control_character, write_to_terminal), making the set predictable.
Three tools is well-scoped for terminal interaction, covering reading, writing, and control without unnecessary bloat.
The tools cover core terminal operations, but missing features like session management or terminal listing are minor gaps for a basic server.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
Connect ChatGPT and Claude to your Mac, Windows or Linux with secure MCP remote access.
Termalin's hosted MCP server. Claude, ChatGPT or any MCP client runs commands, moves files over SFTP, queries databases and reads server metrics and monitoring alerts on your servers, keylessly through Termalin Connectors: no SSH key is handed over and no inbound port is opened. Per-host command policy and an audit log. Needs a termal.in Pro or Team account (new accounts start with a 14-day Pro trial).
