About tmux
tmux is a Go program that exposes one tmux server to MCP clients. It is for developers who want an agent to create, inspect, and operate terminal sessions, with grouped permissions and tools for waiting on pane output or command completion.
Key features
- 01Inspect sessions, windows, and panes
- 02Create and manage sessions and panes
- 03Send input and commands to panes
- 04Wait for text or command completion
- 05Limit client access by toolset
Use cases
- 01Run development work in a separate pane
- 02Wait for test or dev-server output
- 03Inspect terminal state during agent work
- 04Restrict a client to read-only inspection
MCP support
The program exposes one tmux server as MCP tools and communicates over stdin and stdout. The target socket can be selected, and toolsets and environment variables control available operations.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README
mcp
Serve one tmux server to Model Context Protocol clients, built on the tmux module and the Go MCP SDK.
$ go install github.com/libtmux/libtmux-go/mcp/cmd/libtmux-mcp@latest
Releases are numbered 0.1.N, and each release increments N. The API is not
settled: any release may change or remove exported identifiers, and the
changelog marks each break. Pin an exact version to avoid one.
Contents — Quick start · Connect another client · Choose which tmux it drives · See an agent work · Run work and wait for it · The tools · Limiting what a client can do · Settings · The pane it runs in · Known limits · Troubleshooting · An agent-shaped program · Embedding it · Packages · What it leaves out · Support and status · See also
Quick start
You need Go 1.26 or newer and tmux 3.3a or newer on PATH. The install
command above puts libtmux-mcp in GOBIN when that is
set, and in $(go env GOPATH)/bin otherwise.
An MCP client launches it as a subprocess and speaks to it over stdin and
stdout, so nothing stays running. If your shell cannot find libtmux-mcp, add
that directory to PATH.
The Python server installs a command of the same name. Run
command -v libtmux-mcp to see which one comes first, and
libtmux-mcp -version to name this one.
claude mcp add: tell Claude Code about it
$ claude mcp add tmux -- libtmux-mcp
Claude Code starts each server it lists, to check that it connects:
$ claude mcp list
libtmux-mcp -doctor: check what it reaches
$ libtmux-mcp -doctor
It answers without a client in the way, and prints something like this:
libtmux-mcp doctor
tmux: 3.6 (requires 3.3a or newer)
socket: /tmp/tmux-1000/libtmux-mcp (from default dedicated socket)
holds: nothing — no tmux server is running on that socket
(not a fault; tmux starts one when something asks it to)
caller: not running inside a tmux pane
Then ask the client for something only tmux can do, such as "create a tmux session called demo and tell me what panes it has".
Connect another client
Each client takes the same command and the same flags. Connect an MCP client on libtmux.org covers startup and shutdown.
codex mcp add: Codex CLI
$ codex mcp add tmux -- libtmux-mcp
gemini mcp add: Gemini CLI
$ gemini mcp add tmux libtmux-mcp
claude_desktop_config.json: Claude Desktop
Claude Desktop starts its servers without your shell's PATH, so give it the
path command -v libtmux-mcp prints. Flags go in args and the environment in
env:
{
"mcpServers": {
"tmux": {
"command": "/path/to/libtmux-mcp",
"args": ["-socket-name", "my-application"],
"env": {"LIBTMUX_TOOLSETS": "inspect,manage,execute"}
}
}
}
Choose which tmux it drives
The choice is made once, when the server starts. A client cannot change it afterwards. Settings lists the other flags, and the contract has the precedence rules.
-socket-name: pick a socket by name
With no flag, the server drives a tmux server of its own, on a socket named
libtmux-mcp, started with a minimal configuration the package ships. An agent
given that cannot touch the sessions you already have.
Once it has made a session, watch it work from another terminal:
$ tmux -L libtmux-mcp attach
To let it drive the tmux you use every day, name that socket. tmux calls its
usual one default:
$ claude mcp add tmux -- libtmux-mcp -socket-name default
A workspace that tmux-workspace load -L project built
lives on the socket project. To let a client read it and change nothing:
$ claude mcp add tmux \
-e LIBTMUX_TOOLSETS=inspect \
-- libtmux-mcp -socket-name project
-socket-path and -binary: an exact socket and tmux
-socket-path names the socket by its absolute path, and -binary names the
tmux executable. -doctor reports what a choice selects:
$ libtmux-mcp \
-doctor \
-socket-path /tmp/my-application.sock
The environment makes the same choices, which is how a client's configuration sets them:
$ LIBTMUX_SOCKET=my-application libtmux-mcp -doctor
See an agent work
These are the calls examples/agent-workflow makes
to run work in a pane beside its own, and what came back. Cursor tokens are
left out, and each reply shows only the fields that answer the call:
→ split_window {"direction":"right","pane_id":"%0","percent":40}
← {"paneId":"%1"}
→ paste_text {"enter":true,"pane_id":"%1","text":"if sleep 1; then printf 'agent-workflow-%s\\n' ready; else printf 'agent-workflow-%s\\n' failed; fi"}
← {"bytes":97}
→ wait_for_text {"pane_id":"%1","patterns":["agent-workflow-ready"],"stop":["agent-workflow-failed"],"timeout":30}
← {"found":true,"matched":"agent-workflow-ready","outcome":"matched"}
→ run_shell_command {"command":"printf 'bounded work\\n'","pane_id":"%1","timeout":30}
← {"exit_status":0,"output":["bounded work"],"timed_out":false}
The example prints these with -trace, and its page
has the command. The agent drives tmux directly, so nothing is copy-pasted out
of a terminal, and waiting for a server to come up is one call.
Run work and wait for it
For one tmux send-keys, shelling out is shorter. The server earns its keep
once the agent has to wait, watch, inspect, or leave your
terminal alone.
A dev server printing its port, a test run finishing, or a deploy log settling turns a shell-out into a polling loop. That loop reads the shell's echo of its own command and reports success before anything happened.
split_window: make room beside your pane
split_window adds a pane and returns its id. A new pane is
given time to start, so run_shell_command can follow at
once.
The trace splits %0 to the right with "percent":40 and gets back
{"paneId":"%1"}.
wait_for_text: wait for what a pane prints
wait_for_text watches a pane and returns when a pattern
appears, or when a stop pattern appears first.
capture_since returns what a pane wrote since the last
look.
The trace waits for agent-workflow-ready and names agent-workflow-failed as
the stop pattern. It gets "outcome":"matched".
A wait longer than the ceiling is shortened, and the reply says so. The
ceiling is LIBTMUX_MCP_WAIT_MAX_SECONDS.
If the pane goes away mid-wait, the reply's outcome is paneDied and lines
holds what it wrote first. If only the output stream ends and the pane is
alive, it is streamLost. The contract has the rest.
run_shell_command: run a command and read its exit status
run_shell_command waits for the command and returns its
exit status and output, without reading the screen at all.
send_keys and paste_text send input and return.
The trace runs a command that prints "bounded work" and gets back
"exit_status":0.
run_shell_command refuses a pane linked with others by
synchronize-panes, because one exit status cannot describe several panes.
Keep reads small
Other parts of the design exist because an agent's context and its turn are the scarce resources.
- Reads are bounded. Captures keep the newest lines asked for and say what they left out. Searches have fixed limits, which the contract lists.
- One call can make several reads.
call_read_tools_batchanswers a list ofinspectcalls with one row each. - Checking is not capturing. The listing tools report what exists without
reading what any pane shows.
snapshot_panereturns a pane's metadata and content together.
The tools
The tools come in toolsets. A toolset is a named group of tools, and it is what an operator grants or withholds:
inspectreads tmux and what panes show, and changes nothing.managerearranges what exists: it renames, resizes, selects, and moves.executecreates sessions, windows, and panes, and sends input to them.teardownkills sessions, windows, and panes, and clears scrollback.
TOOLS.md has every tool's arguments and what it returns, and the documentation site gives each tool the page linked above. That reference is for searching, which is why it is not here.
Three behaviours matter before you grant execute:
- Input goes where tmux sends it. With
synchronize-paneson, tmux types into every pane of the window.send_keysreports the linked panes before it sends. - A new pane is given time to start. Input tools wait for its shell to
reach the prompt, so
split_windowthenrun_shell_commandworks. - Copy mode is left to the person. Reads never take over an attached
view, and
get_pane_inforeports when a pane is in a mode.
The contract has the rest of each.
Limiting what a client can do
LIBTMUX_TOOLSETS: choose the toolsets
It takes toolset names separated by commas, in any order. Without it the
server grants inspect, manage, and execute.
teardownjoins that default only when this process started the tmux server on thelibtmux-mcpsocket. Everywhere else, ask for it by name.- A value that is set and empty grants no toolset, and there is no
nonekeyword.
To see the effect without a client, list what the server offers with one toolset:
$ LIBTMUX_TOOLSETS=inspect libtmux-mcp -tools
A client gets the same selection from the environment it starts the server with:
$ claude mcp add tmux \
-e LIBTMUX_TOOLSETS=inspect \
-- libtmux-mcp -socket-name default
LIBTMUX_TOOLS and LIBTMUX_EXCLUDE_TOOLS: name exact tools
LIBTMUX_TOOLS adds tools by name to what the
toolsets grant, and
LIBTMUX_EXCLUDE_TOOLS then removes
tools by name. Excluding a tool also removes it from what
call_read_tools_batch may call.
This lists the default tools without send_keys and
send_keys_batch:
$ LIBTMUX_EXCLUDE_TOOLS=send_keys,send_keys_batch libtmux-mcp -tools
A name that matches no tool, or an empty item in either list, stops the server at startup, before it opens tmux.
Choosing tools shapes what a client is offered. Every call runs with your user's authority. The contract covers the variables from earlier releases.
libtmux-mcp -tools: see what a client would be offered
$ libtmux-mcp -tools
It prints the tools the server would advertise: each one's toolset, which processes it can reach, and a sentence on what it does. Give it the flags and environment the client gives the server, because they decide the listing.
tmux://capabilities: what each tool says about itself
Each tool describes what it reaches and changes, under
_meta["com.git-pull.libtmux-mcp/capability"]. The server's one resource,
tmux://capabilities, reports the same descriptions beside the selection in
force. The contract lists them.
Settings
Flags choose the tmux server once, at startup:
| Flag | Meaning |
|---|---|
-socket-path | an explicit socket path; when set, it wins over everything else |
-socket-name | a tmux socket name; when set, it wins over both socket variables below |
-binary | the tmux executable; empty uses LIBTMUX_TMUX_BIN, then finds tmux on PATH |
Other flags answer a question and exit, which is what a config entry that will not start needs:
| Flag | Answers |
|---|---|
-version | which build this is |
-tools | the tools and toolsets a client would see |
-doctor | which socket it reaches, what is on it, and whether it is running inside that tmux itself |
The environment sets the rest:
| Variable | Does |
|---|---|
LIBTMUX_TOOLSETS | selects any unordered subset of the toolsets |
LIBTMUX_TOOLS | includes exact tool names after toolset expansion |
LIBTMUX_EXCLUDE_TOOLS | removes exact names after every inclusion |
LIBTMUX_SOCKET_PATH | selects an absolute socket path; mutually exclusive with LIBTMUX_SOCKET |
LIBTMUX_SOCKET | names the tmux socket when no socket flag selects one |
LIBTMUX_TMUX_CONFIG | selects a nonempty absolute tmux configuration path |
LIBTMUX_TMUX_BIN | selects the tmux executable when -binary is empty |
LIBTMUX_MCP_WAIT_MAX_SECONDS | the longest any one wait may run; 300 by default |
LIBTMUX_AUDIT | stderr, or a path, to record every call |
- A flag wins over its variable, and everything is fixed when the server starts. The names match the Python server's.
- The tmux executable is resolved once. A bad path fails at startup. A tmux server that is not running is fine, because tmux starts one on demand.
- A long wait is shortened. The reply says so in
effectiveTimeoutSecondsandtimeoutClamped.
The contract has the full text.
The pane it runs in
isCaller: knowing its own pane
Every pane the server reports carries isCaller: true for the pane it runs
in, false for any other, and null when the server is not in a pane at all.
get_server_info answers the same question directly.
The server reads TMUX_PANE and TMUX first. When they say nothing, it finds
the pane whose process is one of its own ancestors.
Asking before it types into your terminal
A write to the pane with isCaller true asks you first, through MCP's
elicitation request: a question the client puts to you on the server's behalf.
- Declining fails the call, and a client that cannot ask is refused.
- A batch asks the same way, and declining stops the batch there.
- With
synchronize-paneson, the question covers every pane the input would reach.
The contract has the rest.
Known limits
- Some tools require a newer tmux. Startup and ordinary tools support
3.3a, including
capture_sinceandrun_shell_command. Non-emptypaste_textrequires 3.4 before staging any buffer;wait_for_textpolls withcapture-panebelow 3.7 and follows control output from 3.7. Restricted tools return an explicit version error on older supported daemons. The runtime uses subprocess commands below 3.7 and a retained control connection from 3.7. - Every tool is annotated as destructive.
list_sessionsincluded, each carriesdestructiveHint=trueand noreadOnlyHint. Classify bytmuxEffectsin each tool's_meta. tools/listis large. More than half of it is the_metadescription. A client that wants a smaller reply can ignore_meta.- Some tools spell results differently.
run_shell_command,send_keys,paste_text, andclear_pane_scrollbackreturn fields such asexit_status; the rest return fields such aspaneId. - An empty
TMUXcounts as set. Input tools refuse whenTMUXorTMUX_PANEis set to nothing. Unset them instead.
The contract gives the reason for each, and PARITY.md covers the result spellings.
Troubleshooting
Ask the server first. -doctor answers most of what follows without a client
in the way:
$ libtmux-mcp -doctor -socket-name default
- The client shows no tmux tools. The server never started. Run the command from your client's config by hand.
- Tools are missing.
LIBTMUX_TOOLSETS,LIBTMUX_TOOLS, orLIBTMUX_EXCLUDE_TOOLSshaped the listing.-toolsprints what a client receives. - It sees none of your sessions. Without
-socket-nameit drives a tmux server of its own.-doctornames the socket. - It reaches the wrong tmux. A client's environment is not your shell's,
so
TMUX_TMPDIRfrom your profile may be unset for it. - Sessions you can see are reported as nothing there. Compare the tmux
version
-doctorprints withtmux -V, and point-binaryat the right one. - A command works in your shell but not through a tool.
show_environmentreports what a new pane would inherit.
The contract explains each.
An agent-shaped program
examples/agent-workflow is the whole loop in one
file. It finds its own pane, splits one off, starts work there and waits for
what it prints, runs a command and reads its exit status, then reads back what
it built.
It lives in the repository, outside the module you installed, so run it from a clone:
$ git clone https://github.com/libtmux/libtmux-go.git
$ go -C libtmux-go/mcp run ./examples/agent-workflow -socket-name demo
On a socket with nothing on it, it starts a session there and prints:
no tmux server on that socket yet; starting one
not running inside this tmux server; using active pane %0
split into %1
2 panes in this window while the work runs
the work printed agent-workflow-ready
the command exited 0 and printed:
| bounded work
the window now holds 2 panes: %0 %1
The client and server are joined in memory, so it is one program. The tool
names, schemas, and results are the ones a client sees over stdin and stdout.
Clean up with tmux -L demo kill-server.
Embedding it
mcp.NewServer: serve one tmux server from your own program
mcp.Run serves a tmux server over standard input and output,
which is all the libtmux-mcp command does. For another transport, build an
Instance and connect it yourself.
This block comes from the package's own example test. It connects one end of the SDK's in-memory transport pair and gives the other end to a client:
// Given: ctx context.Context; target tmux.Server; serverTransport sdk.Transport
instance, err := tmuxmcp.NewServer(target)
if err != nil {
return nil, nil, err
}
serverSession, err := instance.Connect(
ctx, tmuxmcp.AssumeResponseCommit(serverTransport), nil,
)
This package is named mcp and so is the SDK's, so the block imports this one
as tmuxmcp and the SDK as sdk. NewServer checks the
target and starts nothing.
mcp.AssumeResponseCommit: say a transport writes each response at once
Standard input and output are known to deliver each response as soon as the
write returns. Wrap any other transport in
AssumeResponseCommit, as the block does for the
in-memory one.
Close the instance when you have finished serving. The reference has the rest of what an embedder is held to, and the contract has the full text.
Packages
mcp: the server as a library
mcp.Run and mcp.NewServer serve a tmux server
to a client. Reference: pkg.go.dev
and libtmux.org.
libtmux-mcp: the command a client launches
It serves one tmux server over stdin and stdout. Reference: pkg.go.dev and the command README.
What it leaves out
- A second tmux server. The server serves one tmux server for the life of the process, and a client cannot name another socket in a call.
- Anything but tools. There is one resource, and no prompts, resource templates, completions, or background job handles.
- Confinement. Toolsets shape what a client is offered. Every call runs
with your user's authority, so a client holding
send_keyscan run anything you can. - The Python server's per-call socket. The socket is chosen once, at launch. PARITY.md lists the other differences.
Support and status
- Go 1.26+ and tmux 3.3a or newer. The server refuses an older tmux before the MCP transport starts. CI runs tmux 3.3a through 3.8.
- Linux, including WSL, and macOS. CI runs this module's tests on Linux across tmux 3.3a through 3.8. macOS is supported on a best-effort basis, and CI coverage for it is highly limited.
- A module of its own.
go geton the tmux library never pulls in the MCP SDK. - Tagged as
mcp/vN. Pin an exact version in your owngo.mod; the commands here fetch the newest.
See also
| Reference | Every exported identifier, method, and field, one page each |
docs/contracts.md | What the server promises beyond this page |
TOOLS.md | Every tool's arguments and results |
PARITY.md | Where this server and the Python one differ |
MIGRATING.md | Settings from earlier releases, and what replaced each |
cmd/libtmux-mcp | The command a client launches |
examples/agent-workflow | The program above, as a directory you can run |
AGENTS.md | Testing the server through a real client, and by hand |
../tmux/ | The library this serves |
| libtmux-mcp in Python | A server for the same tmux and the same clients |
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.