libtmux MCP server
Commit Nov 12, 2026Enables AI agents to manage tmux sessions, windows, and panes by running commands, reading terminal output, and orchestrating terminal environments.
Also known as tmux-python/libtmux-mcp
- Stars
- 14
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 12, 2026
- License
- MIT
What is libtmux MCP?
libtmux enables AI agents to manage tmux sessions, windows, and panes by running commands, reading terminal output, and orchestrating terminal environments.
Summary generated from the project's README
About libtmux MCP server
Managing terminal environments and long-running processes from within an AI agent is what libtmux-mcp enables. This server provides a bridge between Model Context Protocol clients and tmux, allowing agents to create sessions, manage windows, and control individual panes. It is designed for developers using tools like Claude Desktop, Claude Code, Codex CLI, or Gemini CLI to give their AI assistants direct interaction with a terminal environment.
Users can set up the server locally using uvx or by adding it to their client configuration. The server includes specialized tools for sophisticated terminal orchestration, such as run_command for executing shell commands with exit status, wait_for_text to monitor output without constant polling, and capture_since to read only new terminal rows. It also offers pane management through tools like split_window, resize_pane, and send_keys_batch for interacting with text-based user interfaces.
This implementation focuses on efficiency and safety. It uses history suppression to keep agent commands out of shell history and includes safeguards to prevent an agent from accidentally killing its own host session. Developers can further refine the agent's capabilities by using the LIBTMUX_TOOLSETS environment variable to include or exclude specific tool groups like inspect, manage, execute, or teardown.
What you can do with it
- 1Automated test executionAsk an agent to start a new tmux session and run a specific test suite while monitoring the results.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachabletmux-python/libtmux-mcp is public and reachablegithub.com/tmux-python/libtmux-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-12github.com/tmux-python/libtmux-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHublibtmux-mcp
A Model Context Protocol server for tmux, built on libtmux.
[!WARNING] Alpha. Releases carry an
-alphaprerelease tag. The API is not settled, and any release may change or remove exported identifiers without a deprecation period. Pin an exact version. Not recommended for production.
Give your AI agent hands inside the terminal — create sessions, run commands, read output, orchestrate panes.
Tools
| Module | Tools |
|---|---|
| Server | list_servers, list_sessions, create_session, kill_server, get_server_info |
| Batch | call_read_tools_batch |
| Session | list_windows, get_session_info, create_window, rename_session, select_window, kill_session |
| Window | list_panes, get_window_info, split_window, rename_window, select_layout, resize_window, move_window, kill_window |
| Pane | run_command, send_keys, send_keys_batch, paste_text, capture_pane, capture_since, snapshot_pane, search_panes, find_pane_by_position, get_pane_info, wait_for_text, wait_for_channel, signal_channel, display_message, select_pane, swap_pane, resize_pane, set_pane_title, clear_pane, pipe_pane, enter_copy_mode, exit_copy_mode, respawn_pane, kill_pane |
| Options | show_option, set_option |
| Environment | show_environment, set_environment |
| Buffers | load_buffer, paste_buffer, show_buffer, delete_buffer |
| Hooks | show_hooks, show_hook |
Quickstart
Requirements: Python 3.11+, tmux >= 3.2a on $PATH.
The distribution is libtmux-mcp, the import is libtmux_mcp, and the
installed executable is libtmux-mcp.
Install and run:
$ uvx libtmux-mcp
Claude Code
$ claude mcp add tmux -- uvx libtmux-mcp
Codex CLI
$ codex mcp add tmux -- uvx libtmux-mcp
Gemini CLI
$ gemini mcp add tmux uvx -- libtmux-mcp
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"tmux": {
"command": "uvx",
"args": ["libtmux-mcp"]
}
}
}
More clients and JSON config: client setup docs
What it feels like
You: Create a session called "api" and run
pytest tests/api/ -xin it.Agent: Created session
apiwith windowtests. Running pytest now. Here's the output — 14 passed, 2 failed. The failures are intest_auth.py::test_token_refreshandtest_auth.py::test_expired_session. Want me to open those files?
The agent manages tmux directly. No copy-pasting terminal output. No switching windows to check on long-running processes.
When the server earns its keep
For a single tmux send-keys, the server doesn't. It earns its keep
the moment the agent has to wait, inspect, or avoid damaging the
terminal it is using — pytest finishing, a dev server printing its
port, a deploy log settling. The difference then is not more access
to tmux, but a better place to put the control loop.
The server-side moves are:
Running. run_command
sends an authored shell command, waits for deterministic completion,
and returns exit status plus tail-preserved output as one typed value.
The command and its completion signal reach the shell as one
space-prefixed event, so best-effort
history suppression
keeps agent-generated input out of shell history by default. The
alternative — hand-rolled send-keys plus wait-for plus a pane
capture — leaves every typed command, signal included, in shell
history.
Driving. send_keys_batch
sends several ordered raw-input operations for TUIs and persistent
shell interaction. It is deliberately not a workflow DSL; command
completion stays in run_command, and repeated observation stays in
capture_since.
Waiting. wait_for_text
blocks inside the server until a condition fires for output the agent
does not author. The alternative is the model polling capture-pane
in a loop, paying both context tokens and round-trip latency for every
turn.
Reading. snapshot_pane
returns content, cursor, copy-mode state, and scroll offset as one
typed value. The alternative is several tmux invocations stitched
together with regex.
Observing. capture_since
returns a cursor with the current pane content, then returns only
newly written or rewritten rows on follow-up calls. The alternative is
re-sending the same scrollback to the model on every check.
Guarding. The server detects the agent's own pane across sockets
and declines to end its own — kill_session
on itself fails loudly instead of silently terminating the host
environment the agent is running in. LIBTMUX_TOOLSETS
(inspect, manage, execute, teardown) drops whole toolsets from the
client's tool list before any prompt is built. The sets are unordered, so
inspect,teardown is a legal surface. Dropping one is inventory and MCP
tool-call configuration, not containment: an enabled execute tool can type
the equivalent of anything it hides.
Documentation
Full docs, guides, and tool reference: libtmux-mcp.git-pull.com
Development
Clone and install:
$ git clone https://github.com/tmux-python/libtmux-mcp.git
$ cd libtmux-mcp
$ uv sync --all-extras --dev
Run the server locally:
$ uv run libtmux-mcp
Run tests:
$ uv run pytest
See CONTRIBUTING.md for the gates, and WRITING.md for how this project writes prose, docstrings, and MCP tool descriptions.
Related projects
- libtmux — Python API for tmux
- tmuxp — tmux session manager
- The Tao of tmux — the book
Attribution
Please use the following BibTeX template to cite libtmux-mcp in scientific discourse:
@misc{libtmux-mcp,
author = {Tony Narlock},
year = {2026},
note = {https://libtmux-mcp.git-pull.com},
title = {libtmux-mcp: MCP server for tmux}
}
License
MIT
libtmux MCP questions
Is this server ready for production use?
No, the server is currently in Alpha, meaning the API is not settled and releases may change or remove identifiers without notice.
Can the agent run commands without cluttering shell history?
Yes, the run_command tool uses history suppression to keep agent-generated input out of shell history by default.