Iterm
The iterm-mcp server provides Claude and other MCP clients with direct control over active iTerm2 terminal sessions on macOS. It offers three primary tools: `write_to_terminal` to execute commands, `read_terminal_output` to retrieve specific lines of output, and `send_control_character` to send signals like ctrl-c, enabling the model to run commands, inspect results, and interact with REPLs. This integration allows users to delegate terminal tasks to AI models while monitoring activity in real-time, solving the problem of giving language models shell access with efficient token usage and minimal dependencies.
- GitHub stars
- 556
- tools
- 3
- last updated
- Mar 8, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
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.
Writes to the active iTerm terminal, often used to run a command. Returns the number of lines of output produced by the command.
No parameter schema in public metadata yet.
read_terminal_outputReads the requested number of lines from the active iTerm terminal.
Reads the requested number of lines from the active iTerm terminal.
No parameter schema in public metadata yet.
send_control_characterSends a control character to the active iTerm terminal.
Sends a control character to the active iTerm terminal.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
iterm-mcp
A Model Context Protocol server that provides access to your iTerm session.
Main Image
Features
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.
Safety Considerations
Details
- Repository
- github.com/ferrislucas/iterm-mcp