Quickstart

One happy path from zero to a working tool invocation.

1. Install

Pick your MCP client and install method:

With uvx installed:

$ claude mcp add tmux -- uvx libtmux-mcp

Config file: .mcp.json (project) or ~/.claude.json (global)

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:

  1. send_keys mutating — send the command to a tmux pane

  2. wait_for_text readonly — wait for the shell prompt to return (command finished)

  3. capture_pane readonly — 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