Overview
Features
Efficient Token Use
The model can inspect only the output it is interested in, typically the last few lines of output even for long running commands.
Natural Integration
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 REPLs as well as send control characters like ctrl-c, ctrl-z, etc.
Easy on the Dependencies
Built with minimal dependencies and runnable via npx. It's designed to be easy to add to Claude Desktop and other MCP clients; it should just work.
Tool: 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.
Tool: read_terminal_output
Reads the requested number of lines from the active iTerm terminal.
Tool: send_control_character
Sends a control character to the active iTerm terminal.
Who Is This For?
- MCP clients:Integrate iTerm2 with LLMs; monitor and control terminal sessions via MCP.




