Persistent Shell MCP Server

If you already use Persistent Shell MCP, the persistent shell mcp mcp server is the piece that lets your assistant work with it directly. A simplified and elegant MCP server for persistent shell execution via tmux.

What the server does

A Model Context Protocol (MCP) server that provides persistent shell execution through tmux sessions. This server enables AI assistants to execute commands in a persistent shell. This unlocks a lot of possiblities, such as Agent Orchestration...

• Dual-Window Architecture — Each workspace has two windows - exec for command execution and ui for clean output display
• Persistent Workspaces — Execute commands in tmux sessions that persist across MCP client restarts
• Interactive Process Support — Handle long-running processes, REPLs, and interactive commands
• Workspace Isolation — Multiple isolated workspaces for different projects or tasks
• Clean UI Management — Separate windows for execution and user-facing output
• Automatic Session Management — Create, destroy, and monitor workspaces seamlessly

Installation

The server ships on npm as tmux-mcp-server, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

• Prerequisites — The Prerequisites tool exposed by this server
• execute_command — Execute commands that complete quickly and return full output. Uses the exec window
• start_process — Start long-running or interactive processes. Can target either window: - exec window (default): For background processes - ui window: For interactive
• get_output — Capture current terminal output from either window: - ui window (default): Clean user-facing output - exec window: Raw shell with all commands
• send_input — The send_input tool exposed by this server
• stop_process — Stop the currently running process in the exec window (sends Ctrl+C)
• create_workspace — The create_workspace tool exposed by this server
• destroy_workspace — The destroy_workspace tool exposed by this server
• list_workspaces — The list_workspaces tool exposed by this server

Credentials and setup notes

• Node.js 18.0.0 or higher - tmux installed on your system - Ubuntu/Debian: sudo apt install tmux - macOS: brew install tmux - CentOS/RHEL: sudo yum install tmux

Worth knowing first

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Persistent Shell MCP.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Persistent Shell MCP's toolset — Prerequisites, execute_command, start_process and 6 more — is a fair guide to whether it matches your workflow. It is maintained by TNTisdial; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Persistent Shell MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.