claude-mux.mcp
Gives terminal control and multi-agent coordination through tmux sessions, enabling observation, command execution, window and pane management, and cross-session agent messaging.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@claude-mux.mcplist all tmux sessions"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
claude-mux.mcp
MCP server for tmux. Gives Claude Code terminal control and multi-agent coordination through tmux sessions.
Install
claude plugin add claude-mux@rtdThen run /install inside Claude Code to verify dependencies and register the MCP server. It checks for bun and tmux, installs packages, and smoke-tests the server.
To update:
claude plugin update claude-mux@rtdThen run /install again to verify everything is current.
Requirements
tmux —
brew install tmuxon macOS,apt install tmuxon LinuxBun —
curl -fsSL https://bun.sh/install | bash
Manual install (development)
If you're working on the server itself, add to ~/.claude.json:
{
"mcpServers": {
"tmux": {
"command": "bun",
"args": ["/path/to/claude-mux.mcp/server.js"]
}
}
}Related MCP server: Claude Code MCP - Agent Orchestration Platform
Actions
Observe
Action | What it does |
| All sessions. Named ones show windows; numbered ones get a one-line summary. |
| One session in detail, previewing each pane's last visible line. |
| Capture pane output. |
| Last N lines, no pagination. Quick look at what just happened. |
| Delta since last read. Only new lines come back. |
| Read a pane's prior Claude Code sessions from the on-disk JSONL — not scrollback. No |
| Every pane across all sessions with dimensions and running process. |
| Authoritative machine-parseable metadata for dashboards (no params). Tab-delimited rows, row-type letter in column 0 — one |
Act
Action | What it does |
| Literal text, spaces preserved. No Enter appended. |
| Type literal text + Enter, then wait. One call for "run this and show me what happened." |
| Space-separated key tokens: |
| Send keys, poll until prompt appears or output settles. Returns the delta. |
| Wrap a command in start/done markers, return a |
| Check a tracked command's status, exit code, and output by |
Manage
Action | What it does |
| Create a session. |
| Kill a session. |
| Create a window in a session. Returns the target for subsequent calls. |
| Kill a window. |
| Split a pane. Returns the new pane target. |
| Kill a pane. |
| Rename a window. |
Coordinate
Cross-session agent messaging and task ownership. All state lives in tmux global environment and named buffers.
Action | What it does |
| Identify yourself by name. Stored globally so other agents can find you. |
| Remove your registration. |
| List all registered agents across all sessions. |
| Message an agent by name, or |
| Check for new messages. |
| Take a task. Atomic file lock prevents two agents from claiming the same one. |
| Mark a task done, release the lock. |
| List all tasks with owner and status. |
Workers
Spawn Claude Code instances as coordinating agents. Each worker gets a name, a team roster, and auto-injected inbox hooks so messages arrive without polling.
Action | What it does |
| One-shot |
| Same, but the window stays open for inspection. |
| Interactive |
| Kill a worker, clean up registration and temp files. |
| Read a completed worker's captured output. |
Design notes
Plain text responses. list returns indented text, not nested JSON. Fewer tokens, easier for the model to parse.
Self-awareness. The server reads $TMUX_PANE on startup and reports you are here: main:0.1 in listings so the model knows which pane is itself.
type vs keys. keys splits on spaces — each token is a tmux key name. Good for Escape :q! Enter, destroys prose. type sends literal text with spaces intact.
exec/result for long commands. typewait blocks up to 30 seconds. exec drops start/done markers, returns a commandId immediately, and result checks on it later. Auto-detects zsh, bash, or fish.
Completion detection. keyswait and typewait poll every 500ms. Shell prompt means done. Output unchanged for 2s means settled. 30s timeout ceiling.
Atomic task claiming. claim uses O_EXCL file creation so two agents racing for the same task can't both win.
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ryanthedev/claude-mux.mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server