Interminal - Acesso Terminal via MCP
QiuwenZheng/interminal
Acesso SSH e shell local direto para o Claude com sessões persistentes
Ver no GitHubServidor MCP leve que fornece ao Claude acesso a terminais SSH e locais com suporte a comandos interativos e de longa duração. Integra-se nativamente com multiplexadores como Zellij para manter estado persistente entre chamadas, ideal para fluxos de trabalho multi-etapas em desenvolvimento, debugging e deploy.
Instalação
npx convez-ai QiuwenZheng/interminal1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Executar scripts e comandos remotos via SSH durante sessões de coding
- Automação de deploys e operações DevOps com feedback em tempo real
- Debugging e troubleshooting em servidores remotos com persistência de estado
- Desenvolvimento multi-etapas que exigem ambiente compartilhado entre chamadas
Veredito

Ferramenta prática para quem precisa que Claude execute operações reais em infraestrutura. Implementação sólida com suporte a sessões persistentes via Zellij e controle fino de processos (Ctrl+C, setas, etc). Ideal para automação de deploy e debugging remoto, mas exige confiança no acesso que você está delegando.
README
A tradução para o português deste README ainda está na fila.
Interminal
Lightweight MCP server that gives AI assistants terminal access — SSH and local shells — with support for interactive and long-running commands.
Installation
# Run directly, no install needed (recommended)
uvx mcp-interminal
# Or install permanently
pip install mcp-interminal
Requires Python ≥ 3.11.
MCP Client Configuration
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"interminal": {
"command": "uvx",
"args": ["mcp-interminal"]
}
}
}
Cursor / other clients: same command + args format above.
Tools
| Tool | Description |
|---|---|
connect_ssh | Connect to an SSH server; returns session_id and welcome banner |
create_local | Create a local shell session |
execute | Run a command; returns output or status=partial + command_id for long-running commands |
read_output | Poll a running command for new output without sending input |
respond | Send text input to a command waiting at a prompt |
send_control | Send control keys: ctrl+c, ctrl+z, arrow keys, F-keys, etc. |
disconnect | Close a session and release all resources |
list_sessions | List all active sessions |
Recommended: Install Zellij
Each execute call runs in an isolated channel — there is no persistent shell between calls. For simple tasks, chaining with && works. For multi-step workflows (project development, debugging, deployment), a terminal multiplexer provides persistent state that survives across calls.
Zellij is strongly recommended on the host machine (local or remote):
# Linux / macOS / WSL
cargo install zellij # or: brew install zellij
# Check if installed
zellij --version
With Zellij installed, the AI agent will automatically create a persistent session where cd, environment variables, virtual environments, and long-running processes carry over naturally. As a bonus, you can run zellij attach <session-name> to watch the AI's terminal work in real-time.
Key Behaviors
- Stateless execute — each call is an isolated channel;
cd /foodoes not persist. Simple tasks: chain with&&. Multi-step workflows: the AI will use a Zellij session for persistent state - Long-running commands return
status="partial"with acommand_id; poll withread_outputor send input withrespond - TUI apps (zellij, vim, htop) must be started in the foreground — never background with
&; after the server daemonizes, the partial channel can be abandoned - SSH PTY is 500×200 xterm-256color so multiplexer sessions render at your actual terminal size
Optional Dependencies
pip install "mcp-interminal[pty]" # Windows PTY support (pywinpty)
pip install "mcp-interminal[ansi]" # ANSI escape rendering (pyte)
pip install "mcp-interminal[pty,ansi]" # both