Skip to main content
Glama
enwaiax

Shuttle

by enwaiax
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

🚀 Shuttle

Secure SSH gateway for AI assistants

MCP CI codecov PyPI Downloads Python Docs License

Shuttle lets AI assistants (Claude Code, Cursor, etc.) securely execute commands on your remote SSH servers — with connection pooling, session isolation, command safety rules, and a web audit panel.

Getting Started · MCP Tools · Web Panel · Security Rules · Docs · 中文文档

Why Shuttle?

When AI coding assistants need to operate remote servers (run tests on GPU machines, deploy to staging, check logs), they need a secure bridge. Shuttle provides:

  • 🔐 4-Level Command Security — Block dangerous commands, require confirmation for risky ones, warn on installs, allow the rest

  • 🔄 Connection Pooling — Reuse SSH connections across commands, no repeated handshakes

  • 📦 Session Isolation — Each AI conversation gets its own working directory context

  • 🌐 Web Audit Panel — See every command the AI ran, per node, with full stdout/stderr

  • 🛡️ Per-Node Rules — Different security policies for prod vs dev servers

  • ⚡ Jump Host Support — Connect through bastion/jump servers

Related MCP server: ssh-mcp-server

Getting Started

1. Install

# Recommended: install CLI once (tools bin on PATH)
uv tool install shuttle-mcp
shuttle --help

# Or run without installing (stdio / one-off)
uvx shuttle-mcp --help

# Older PyPI wheels without the `shuttle-mcp` script:
# uvx --from shuttle-mcp shuttle --help

2. Add your first node

shuttle node add
# Follow the prompts: name, host, username, password/key

3. Connect to your AI assistant

Claude Code / Cursor (stdio mode):

// .mcp.json
{
  "mcpServers": {
    "shuttle": {
      "command": "uvx",
      "args": ["shuttle-mcp"]
    }
  }
}

Service mode (with Web UI):

# Start the service
shuttle serve

# Then configure your AI client with the URL
// .mcp.json
{
  "mcpServers": {
    "shuttle": {
      "url": "http://localhost:9876/mcp/"
    }
  }
}

That's it. Your AI assistant can now execute commands on your remote servers.

Two Running Modes

Mode

Command

MCP Transport

Web UI

Use Case

CLI

shuttle

stdio

❌

Quick use, AI client manages lifecycle

Service

shuttle serve

streamable-http

✅ http://localhost:9876

Audit logs, manage rules, cloud deploy

Both modes share the same SQLite database — commands logged in CLI mode are visible in the Web UI when you switch to service mode.

MCP Tools

AI assistants get these tools automatically:

Tool

Description

ssh_run

Run a command on a remote node (sessions auto-managed)

ssh_upload

Upload a file via SFTP

ssh_download

Download a file via SFTP

ssh_list_nodes

List all configured nodes

ssh_add_node

Add a new SSH node

Example conversation

You: Check the GPU usage on my training server
AI:  → ssh_run(node="gpu-server", command="nvidia-smi")
AI:  Your GPU server has 7x A100-80GB, all idle at 0% utilization.

You: Start a training run
AI:  → ssh_run(node="gpu-server", command="cd /workspace && python train.py")
AI:  Training started. Epoch 1/10... (working directory preserved automatically)

Security Rules

Commands are evaluated against a 4-level security system:

Level

Behavior

Example

🔴 block

Rejected immediately

rm -rf /, mkfs, fork bomb

🟡 confirm

Requires user confirmation

sudo, rm -rf, shutdown

🟠 warn

Executes with warning logged

apt install, pip install

🟢 allow

Executes normally

Everything else

Default rules are seeded on first startup. Customize via Web UI or directly in the database.

Per-Node Overrides

Different servers can have different rules:

Global: sudo .* → confirm
GPU Server: sudo .* → allow (trusted environment)
Prod Server: DROP TABLE → block (extra protection)

Web Panel

Start with shuttle serve, open http://localhost:9876:

  • Overview — Node cards with status, quick stats

  • Activity — Per-node command log (console-style, with stdout/stderr)

  • Security Rules — Manage global defaults and per-node overrides

  • Settings — Connection pool and cleanup configuration

The Web UI requires a bearer token (displayed when you run shuttle serve).

CLI Reference

# MCP Server
shuttle                      # Start MCP server (stdio mode)
shuttle serve                # Start service mode (MCP + Web)
shuttle serve --port 8080    # Custom port
shuttle serve --host 0.0.0.0 # Bind to all interfaces

# Node Management
shuttle node add             # Add node interactively
shuttle node list            # List all nodes
shuttle node test <name>     # Test SSH connection
shuttle node edit <name>     # Edit a node
shuttle node remove <name>   # Remove a node

# Configuration
shuttle config show          # Display current config

Configuration

All settings can be overridden with environment variables (prefix SHUTTLE_):

Variable

Default

Description

SHUTTLE_DB_URL

sqlite+aiosqlite:///~/.shuttle/shuttle.db

Database URL

SHUTTLE_WEB_PORT

9876

Web panel port

SHUTTLE_POOL_MAX_TOTAL

50

Max total SSH connections

SHUTTLE_POOL_MAX_PER_NODE

5

Max connections per node

SHUTTLE_POOL_IDLE_TIMEOUT

300

Idle connection timeout (seconds)

Using PostgreSQL

SHUTTLE_DB_URL=postgresql+asyncpg://user:pass@host:5432/shuttle shuttle serve

Requires: uv pip install asyncpg (install into the same environment that runs Shuttle)

Development

# Clone and install
git clone https://github.com/enwaiax/shuttle.git
cd shuttle
uv sync

# Run tests
uv run pytest tests/ -v

# Lint
uv run ruff check src/ tests/

# Frontend dev (hot reload)
cd web && npm install && npm run dev
# Backend: uv run shuttle serve (in another terminal)

Architecture

Developer ↔ AI Assistant ↔ Shuttle (MCP) ↔ SSH ↔ Remote Servers
                              │
                    ┌─────────┴──────────┐
                    │   Core Engine       │
                    │  ├ ConnectionPool   │
                    │  ├ SessionManager   │
                    │  ├ CommandGuard     │
                    │  └ SQLAlchemy ORM   │
                    └────────────────────┘

Service mode: Single ASGI app serving both MCP (at /mcp/) and Web UI (at /) on the same port.

License

MIT

This server cannot be installed

A
license - permissive license
-
quality - not tested
C
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
2dRelease cycle
4Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • MCP SSH Orchestrator

    samerfarida
    A
    license
    B
    quality
    A
    maintenance
    Provides policy-driven, auditable SSH access to server fleets for AI assistants with zero-trust security controls, command whitelisting, and comprehensive audit logging to safely manage infrastructure.
    Last updated
    13
    26
    Apache 2.0

  • ssh-mcp-server

    ZachFlint
    A
    license
    A
    quality
    C
    maintenance
    Enables AI assistants to securely execute remote SSH commands, perform file transfers, and monitor system status through a standardized interface. It features robust security controls including command whitelisting, blacklisting, and credential isolation to prevent unauthorized operations.
    Last updated
    10
    44
    MIT

  • SSH MCP Server

    uarlouski
    A
    license
    -
    quality
    B
    maintenance
    Enables AI assistants to securely execute commands, transfer files, and manage port forwarding on remote servers via SSH.
    Last updated
    135
    36
    Apache 2.0

View all related MCP servers

Related MCP Connectors

  • emisar

    Let AI operate servers without SSH. Choose actions, approve risky changes, and audit every step.

  • SentinelX

    Operate your Linux servers from your LLM. Every action runs through an auditable allowlist.

  • proxykey

    Issue, rotate and revoke scoped API-key passes for 25+ providers — the agent never sees a real key

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/enwaiax/shuttle'

If you have feedback or need assistance with the MCP directory API, please join our Discord server