Quickstart¶
One happy path from zero to a working tool invocation.
1. Install¶
Pick your MCP client and install method:
See MCP Clients for dev-checkout setup, full config-file locations, and common pitfalls.
2. Verify¶
Ask your LLM:
Prompt
List all my tmux sessions and show me what’s running in each pane.
The agent will call list_sessions, then list_panes and capture_pane to inspect your workspace. You should see your tmux sessions, windows, and pane contents in the response.
3. Try it¶
Here are a few things to try:
Prompt
Create a new tmux session called “workspace” with a window named “build”.
Prompt
Send make test to the pane in my build window, then wait for it to finish and capture the output.
Prompt
Search all my panes for the word “error”.
How it works¶
When you say “run make test and show me the output”, the agent executes a three-step pattern:
send_keysmutating — send the command to a tmux panewait_for_textreadonly — wait for the shell prompt to return (command finished)capture_panereadonly — read the terminal output
This send → wait → capture sequence is the fundamental workflow. Most agent interactions with tmux follow this pattern or a variation of it.
Next steps¶
Concepts — Understand the tmux hierarchy and how tools target panes
Configuration — Environment variables and socket isolation
Safety tiers — Control which tools are available
Tools — Browse all available tools