Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
Nothing to run from here
Tmux is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
7
downloads a day
local
runs on your machine
215
downloads in 30d
What it does
Model Context Protocol server that lets LLMs collaboratively drive tmux
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user k8ika0s-tmux-mcp '--' npx -y @k8ika0s/mcp-tmux
# 2 — ask your agent for something these tools do
# tmux_set_default, tmux_get_default, tmux_open_session and 34 more
Tmux costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
K8All 1 server
k8ika0s1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Tmux as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user k8ika0s-tmux-mcp '--' npx -y @k8ika0s/mcp-tmuxReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take MCP_TMUX_HOST (Optional default SSH host alias to use when none is provided.), MCP_TMUX_SESSION (Optional default tmux session name to use when none is provided.), TMUX_BIN (Optional path to tmux binary if not on PATH.), MCP_TMUX_TIMEOUT_MS (Timeout in milliseconds for tmux/ssh invocations (default 15000).), MCP_TMUX_LOG_DIR (Override log directory (defaults to ~/.config/mcp-tmux/logs).), MCP_TMUX_HOSTS_FILE (Optional JSON file for per-host tmux PATH/bin overrides.) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
37 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Persist defaults for later tool calls. Omit fields you do not want to change.
No parameter schema on file.
Display the current remembered defaults.
No parameter schema on file.
Given an ssh host alias and session name, ensure the remote tmux session exists (create if missing) and set it as default for subsequent commands.
No parameter schema on file.
Returns the default session (if any) and a quick layout snapshot.
No parameter schema on file.
Return sessions, windows, panes, and the last lines of the active/default pane.
No parameter schema on file.
Readonly variant of tmux_state to retrieve sessions, windows, panes, and recent capture without modifying defaults.
No parameter schema on file.
Capture recent scrollback from a pane or session to infer context; also extracts recent commands heuristically.
No parameter schema on file.
Returns a concise how-to for using the tmux MCP tools safely.
No parameter schema on file.
Return the running server version and package identifier for verification.
No parameter schema on file.
Enable or disable verbose audit logging for a host/session (logs commands and outputs).
No parameter schema on file.
Return window layouts for a session so they can be restored later.
No parameter schema on file.
Apply a saved layout string to a target window.
No parameter schema on file.
Poll a pane multiple times to watch output without reissuing commands.
No parameter schema on file.
Send the same keys to multiple targets (across hosts) and optionally capture results.
No parameter schema on file.
Select a window so subsequent commands target it.
No parameter schema on file.
Select a pane so subsequent commands target it.
No parameter schema on file.
Enable or disable synchronize-panes for a window.
No parameter schema on file.
Capture layouts for all windows in a session and store them under a profile name.
No parameter schema on file.
Apply a previously saved layout profile to a session. Windows are matched by index; pane counts must be compatible.
No parameter schema on file.
Check tmux availability, PATH/bin resolution, and session listing for a host.
No parameter schema on file.
Enumerate sessions with attachment counts and window totals.
No parameter schema on file.
List windows within a session (or all sessions if no target provided).
No parameter schema on file.
List panes across windows or inside a specific target.
No parameter schema on file.
Read the scrollback of a pane to observe command results.
No parameter schema on file.
Capture scrollback from multiple panes in parallel (readonly).
No parameter schema on file.
Send keystrokes to a tmux target, optionally appending Enter.
No parameter schema on file.
Execute multiple shell commands sequentially in one tmux pane and capture the output. Uses
No parameter schema on file.
Create a detached tmux session to collaborate in.
No parameter schema on file.
Create a window in a target session, useful for side-by-side collaboration.
No parameter schema on file.
Split a pane horizontally or vertically, optionally running a command.
No parameter schema on file.
Terminate a tmux session. Use with care.
No parameter schema on file.
Close a tmux window. Use with care.
No parameter schema on file.
Close a tmux pane. Use with care.
No parameter schema on file.
Rename a tmux session.
No parameter schema on file.
Rename a tmux window.
No parameter schema on file.
Execute any tmux subcommand with raw args. Use this when helpers do not cover your use case. You are responsible for correctness and safety.
No parameter schema on file.
Run a tmux command and return raw stdout/stderr for debugging remote formatting/quoting issues.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under AGPL-3.0
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Tmux or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 0.1.10 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings1 threat · 15 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest5ee53cec940382f9b034d20d65be95516e08776309637010380ce4cde55f886a
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (37 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
37 of the 37 recovered tools are registered only when values.version is false (dist/index.js:708) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
No tool is registered unconditionally · 37 only when values.version is false (dist/index.js:708) — typically when a key or option is configured. All 37 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| tmux_set_default conditional | no tags | |
| tmux_get_default conditional | no tags | |
| tmux_open_session conditional | code-exec | code-exec: parameter "command" |
| tmux_default_context conditional | no tags | |
| tmux_state conditional | no tags | |
| tmux_readonly_state conditional | no tags | |
| tmux_context_history conditional | no tags | |
| tmux_quickstart conditional | no tags | |
| tmux_server_info conditional | no tags | |
| tmux_set_audit_logging conditional | no tags | |
| tmux_capture_layout conditional | no tags | |
| tmux_restore_layout conditional | no tags | |
| tmux_tail_pane conditional | no tags | |
| tmux_multi_run conditional | no tags | |
| tmux_select_window conditional | no tags | |
| tmux_select_pane conditional | no tags | |
| tmux_set_sync_panes conditional | no tags | |
| tmux_save_layout_profile conditional | no tags | |
| tmux_apply_layout_profile conditional | no tags | |
| tmux_health conditional | no tags | |
| tmux_list_sessions conditional | no tags | |
| tmux_list_windows conditional | no tags | |
| tmux_list_panes conditional | no tags | |
| tmux_capture_pane conditional | no tags | |
| tmux_batch_capture conditional | no tags | |
| tmux_send_keys conditional | no tags | |
| tmux_run_batch conditional | code-exec | code-exec: parameter "command" |
| tmux_new_session conditional | code-exec | code-exec: parameter "command" |
| tmux_new_window conditional | code-exec | code-exec: parameter "command" |
| tmux_split_pane conditional | code-exec | code-exec: parameter "command" |
| tmux_kill_session conditional | no tags | |
| tmux_kill_window conditional | no tags | |
| tmux_kill_pane conditional | no tags | |
| tmux_rename_session conditional | no tags | |
| tmux_rename_window conditional | no tags | |
| tmux_command conditional | no tags | |
| tmux_debug_raw conditional | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest5ee53cec940382f9
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.10. Pin a release below and the command asks for exactly that one.
0.1.10
14 Dec 2025
latestNo release note was published with this version.
0.1.7
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Tmux can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.