Quick Start

Get Station running with production-ready security agents in 3 simple steps.

🚀 3-Step Setup

1. Install Station

curl -fsSL https://raw.githubusercontent.com/cloudshipai/station/main/install.sh | bash

2. Initialize and Install Security Bundle

# Initialize Station with Ship integration
stn init --ship

# Install DevOps Security Bundle
stn bundle install https://github.com/cloudshipai/registry/releases/latest/download/devops-security-bundle.tar.gz security

What is Ship? Ship provides curated MCP tools for Station. The --ship flag automatically configures Station with production-ready tools for development workflows.

3. Sync and Connect

Sync your MCP tools and agents:

stn sync

Connect to Claude Code:

echo '{
  "mcpServers": {
    "station": {
      "command": "stn",
      "args": ["stdio"]
    }
  }
}' > ~/.claude_desktop_config.json

✅ You’re Ready!

Open the Station UI: http://localhost:8585

View your MCP servers and tools:

Test your security agents:

stn agent run "Security Scanner" "Scan the current directory for security vulnerabilities"

Check execution results:

Connect to Claude Code - Station MCP tools are now available for creating agents, running security scans, and managing environments through natural conversation.

🎯 What You Get

• 2 Production-Ready Agents: Security Scanner + Terraform Auditor
• 16 Security Tools: Checkov, TFLint, and more via Ship CLI
• Visual Interface: See MCP connections, agent runs, and tool availability
• Claude Code Integration: Create and run agents through natural conversation
• CI/CD Ready: Use in GitHub Actions, GitLab CI, or any container environment

Access Methods

Station provides multiple ways to interact with your agents:

Command Line

# Direct agent execution
stn agent run 1 "task description"

# List agents
stn agent list

# Check system status
stn status

SSH/TUI Access

# Access admin interface via SSH
ssh admin@localhost -p 2222

Interactive terminal interface for managing agents and viewing logs.

REST API

# Queue agent execution
curl -X POST http://localhost:8080/api/v1/agents/1/queue \
  -H "Content-Type: application/json" \
  -d '{"task": "Check system status"}'

WebSocket

Real-time updates and streaming responses for agent execution and system events.

Development Workflow

1. Create Agent - stn agent create to define your agent
2. Test Locally - stn agent run to test functionality
3. Export Template - stn agent export to create reusable templates
4. Version Control - git add & commit for your agent configurations
5. Deploy - Copy template configs and sync in production environment
6. Monitor - Use SSH/API access to monitor execution

Next Steps

• Learn the Architecture - Understand how Station manages agents and tools
• MCP Quick Start - Get running with Claude Desktop in 5 minutes
• Create Bundles - Package and share your agents
• Why Station? - Understand the use cases

System Requirements

• OS: Linux, macOS, Windows
• Memory: 512MB RAM minimum, 1GB recommended
• Storage: 200MB for runtime, 1GB+ for production data
• Database: SQLite (built-in, no setup required)
• Network: Outbound HTTPS for AI providers and tool integrations