This MCP server allows AI agents to work with TMUX as a termnial session manager
LocalAbout This MCP server allows AI agents to work with TMUX as a termnial session manager
This MCP server lets AI agents interact with tmux sessions through libtmux. It supports session recording, background operation, and work across multiple windows and panes, which can help with auditing terminal activity.
Key features
- 01Interact with tmux sessions
- 02Record sessions
- 03Run processes in the background
- 04Work across multiple windows and panes
- 05Choose a session name
Use cases
- 01Reviewing agent activity in terminals
- 02Recording terminal sessions for audits
- 03Running agent tasks in the background
- 04Managing work across tmux panes
MCP support
The MCP server exposes shell interaction through tmux to AI agents. The README also mentions a test MCP client in the client directory.
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 READMEThis MCP server allows AI agents to work with TMUX as a termnial session manager
This is very useful for auditing purposes, keeping an eye open on your AI agent actions across your terminals. As well as session recording, background operation and allowing AI agents to work with multiple windows panes and tmux sessions.
By default, a session named agent-terminal is used by the mcp-server. you can instuct the AI to use another session if desired.
Tests: The client directory contains a test mcp client as well as other pytests that can be invoked using ./run-tests.sh
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.