AI drives one persistent tmux-backed terminal over MCP; ssh, containers & agent TUIs nest in it.
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.
This image represents different intelligences sharing one persistent workspace and advancing the same work from their own perspectives.
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 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 backcron — a scheduled run can launch an agent and collect its outputclaude_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: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.
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.
| Tool | What it does |
|---|---|
| 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: |
{
"mcpServers": {
"aiterm": {
"command": "npx",
"args": ["-y", "aiterm-mcp"],
"env": {
"GROK_AUTH_PATH": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| GROK_AUTH_PATH | Filesystem location the server is allowed to use. | Optional |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.