Aiterm MCP Server

AI drives one persistent tmux-backed terminal over MCP; ssh, containers & agent TUIs nest in it.

Local serverstdioPython

What is the Aiterm MCP server?

Most AI and media services work still happens through a UI a human drives. Aiterm MCP server moves it into the conversation instead. AI drives one persistent tmux-backed terminal over MCP; ssh, containers & agent TUIs nest in it.

The short version

This image represents different intelligences sharing one persistent workspace and advancing the same work from their own perspectives.

Getting it running

Installation goes through your MCP client rather than a global install: point it at aiterm-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

The tools it exposes

The server publishes 7 tools. What each one is for:

  • Multi — agent orchestration** — an orchestrator hands sub-tasks to Codex / Grok / Composer, each in its own persistent session, and reads them all back
  • cron — a scheduled run can launch an agent and collect its output
  • claude_agent — Claude Code CLI (Anthropic)
  • codex_agent — Codex CLI (OpenAI; terminal config/CLI default unless overridden)
  • grok_agent — Grok Build, model grok-4.5 by default (model? overrides) (xAI)
  • composer_agent — Grok Build, model grok-composer-2.5-fast by default (model? overrides) (xAI)
  • Cursor — Save this as .cursor/mcp.json for the project, or ~/.cursor/mcp.json globally:

What it needs from you

Configuration is passed through the environment: GROK_AUTH_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Things to watch

  • 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.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Aiterm's toolset — Multi, cron, claude_agent and 4 more — is a fair guide to whether it matches your workflow. It is maintained by kitepon-rgb; worth a glance at recent repository activity before you build anything load-bearing on it.

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

Available tools

ToolWhat it does
Multiagent orchestration** — an orchestrator hands sub-tasks to Codex / Grok / Composer, each in its own persistent session, and reads them all back.
crona scheduled run can launch an agent and collect its output.
claude_agentClaude Code CLI (Anthropic)
codex_agentCodex CLI (OpenAI; terminal config/CLI default unless overridden)
grok_agentGrok Build, model grok-4.5 by default (model? overrides) (xAI)
composer_agentGrok Build, model grok-composer-2.5-fast by default (model? overrides) (xAI)
CursorSave this as .cursor/mcp.json for the project, or ~/.cursor/mcp.json globally:

How to install the Aiterm MCP server

{
  "mcpServers": {
    "aiterm": {
      "command": "npx",
      "args": ["-y", "aiterm-mcp"],
      "env": {
        "GROK_AUTH_PATH": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
GROK_AUTH_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Aiterm to Multi.
  • Use Aiterm to cron.
  • Use Aiterm to claude agent.

Frequently asked questions

It connects Aiterm to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (Multi, cron, claude_agent, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Aiterm directly.