Quickstart

Prerequisites

Docker - Required for:
- Jaeger - OTEL tracing backend for observability
- Ship CLI - MCP tools for filesystem operations
- Sandbox - Isolated container for agent code execution
- stn up - Run environments/bundles in containers
AI Provider - Choose one:
- OpenAI API Key (recommended) - gpt-5, gpt-5-mini, etc.
- Google Gemini API Key
- Anthropic API Key - pay-per-token billing

Step 1: Install Station

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

Verify the installation:

stn --version

Step 2: Initialize with Your AI Provider

Anthropic OAuth Unavailable: Anthropic has restricted third-party OAuth tokens. Claude Max/Pro subscription authentication is not working until further notice. Please use API key authentication instead.

OpenAI (Recommended)
Google Gemini
Anthropic (API Key)

export OPENAI_API_KEY="sk-..."
stn init --provider openai --ship

Defaults to gpt-5-mini.

export GEMINI_API_KEY="..."
stn init --provider gemini --ship

export ANTHROPIC_API_KEY="sk-ant-api03-..."
stn init --provider anthropic --ship

Uses pay-per-token billing (not Claude Max/Pro subscription).

What is Ship? Ship is an MCP CLI tool that provides filesystem and development tools for Station agents.

Git-Backed Workspace (Optional)

For version-controlled agent configurations:

# Initialize in a specific directory
stn init --provider openai --ship --config ~/my-station-workspace

# Your agents, MCP configs, and variables are now version-controllable
cd ~/my-station-workspace
git init && git add . && git commit -m "Initial Station config"

Step 3: Start Jaeger (Tracing)

Start the Jaeger tracing backend for observability:

stn jaeger up

Jaeger UI available at http://localhost:16686.

Step 4: Connect Your MCP Client

Claude Code CLI
Claude Desktop
Cursor
OpenCode

claude mcp add station -e OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318 --scope user -- stn stdio

Verify: claude mcp listWith custom workspace:

claude mcp add station -e OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318 --scope user -- stn stdio --config ~/my-station-workspace

Edit your config file:

OS	Path
macOS	`~/Library/Application Support/Claude/claude_desktop_config.json`
Windows	`%APPDATA%\Claude\claude_desktop_config.json`
Linux	`~/.config/Claude/claude_desktop_config.json`

{
  "mcpServers": {
    "station": {
      "command": "stn",
      "args": ["stdio"],
      "env": {
        "OTEL_EXPORTER_OTLP_ENDPOINT": "http://localhost:4318"
      }
    }
  }
}

With custom workspace:

{
  "mcpServers": {
    "station": {
      "command": "stn",
      "args": ["stdio", "--config", "/path/to/my-station-workspace"],
      "env": {
        "OTEL_EXPORTER_OTLP_ENDPOINT": "http://localhost:4318"
      }
    }
  }
}

Add to .cursor/mcp.json in your project (or ~/.cursor/mcp.json for global):

{
  "mcpServers": {
    "station": {
      "command": "stn",
      "args": ["stdio"],
      "env": {
        "OTEL_EXPORTER_OTLP_ENDPOINT": "http://localhost:4318"
      }
    }
  }
}

Add to opencode.jsonc:

{
  "mcp": {
    "station": {
      "enabled": true,
      "type": "local",
      "command": ["stn", "stdio"],
      "environment": {
        "OTEL_EXPORTER_OTLP_ENDPOINT": "http://localhost:4318"
      }
    }
  }
}

Step 5: Start Using Station

Restart your editor. Station provides:

Web UI at http://localhost:8585 for configuration
Jaeger UI at http://localhost:16686 for traces
41 MCP tools available in your AI assistant

Try your first command:

"Show me all Station MCP tools available"

Step 6: Interactive Hands-On Tutorial (Optional)

Ready to dive deeper? Copy this prompt into your MCP client (Claude, Cursor, etc.) for a guided, interactive tour of Station’s features:

Interactive Tutorial Prompt

You are my Station onboarding guide. Walk me through an interactive hands-on tutorial.

RULES:
1. Create a todo list to track progress through each section
2. At each section, STOP and let me engage before continuing
3. Use Station MCP tools to demonstrate - don't just explain, DO IT
4. Keep it fun and celebrate wins!

THE JOURNEY:

## 1. Hello World Agent
- Create a "hello-world" agent that greets users and tells a joke
- Call the agent and show the result
- NOTE: Agent execution may take 10-30 seconds depending on your AI model
- Point me to http://localhost:8585 to see the agent in the UI
[STOP for me to try it]

## 2. Faker Tools & MCP Templates
- Explain Faker tools (AI-generated mock data for safe development)
- Note: Real MCP tools are added via Station UI or template.json
- Explain MCP templates - they keep credentials safe when deploying
- Create a "prometheus-metrics" faker for realistic metrics
- IMPORTANT: Faker tool calls can take 30-60+ seconds as the AI generates realistic mock data. This is normal!
- Show me results at http://localhost:8585
[STOP to see the faker]

## 3. DevOps Investigation Agent
- Create a "metrics-investigator" agent using our prometheus faker
- Call it: "Check for performance issues in the last hour"
- NOTE: This may take a minute as the agent uses faker tools to simulate real metrics
- Direct me to http://localhost:8585 to inspect the run
[STOP to review the investigation]

## 4. Multi-Agent Hierarchy
- Create an "incident-coordinator" that delegates to:
  - metrics-investigator (existing)
  - logs-investigator (new - create a logs faker)
- Show hierarchy structure in the .prompt file
- Call coordinator: "Investigate why the API is slow"
- Multi-agent runs take longer as each agent executes sequentially
- Check out the delegation chain at http://localhost:8585
[STOP to see delegation]

## 5. Inspecting Runs
- Use inspect_run to show detailed execution
- Explain: tool calls, delegations, timing
- Compare with the visual view at http://localhost:8585
[STOP to explore]

## 6. Workflow with Human-in-the-Loop
- Create a workflow: investigate → switch on severity → human_approval if high → report
- Make it complex (switch/parallel), not sequential
- Start the workflow
- Show me the workflow state at http://localhost:8585
[STOP for me to approve/reject]

## 7. Evaluation & Reporting
- Run evals with evaluate_benchmark
- Generate a performance report
- View detailed metrics at http://localhost:8585
[STOP to review]

## 8. Grand Finale
- Direct me to http://localhost:8585 (Station UI)
- Quick tour: Agents, MCP servers, Runs, Workflows
- Celebrate!

## 9. Want More? (Optional)
Briefly explain these advanced features (no demo needed):
- **Schedules**: Cron-based agent scheduling
- **Sandboxes**: Isolated code execution (Python/Node/Bash)
- **Notify Webhooks**: Send alerts to Slack, ntfy, Discord
- **Bundles**: Package and share agent teams
- **Deploy**: `stn deploy` to Fly.io, Docker, K8s
- **CloudShip**: Centralized management and team OAuth

Start now with Section 1!

Performance Note: Faker tools generate AI-powered mock data, which can take 30-60+ seconds per call. This is normal! Real MCP tools (like Prometheus, Datadog) are much faster since they query actual APIs.

Next Steps

Create Agents

Build custom AI agents with prompts and tools

Add MCP Tools

Connect MCP servers to give your agents powerful tools

Multi-Agent Teams

Create agent hierarchies with coordinators and specialists

GitOps Workflow

Version control your agents and collaborate with your team

Get Started

Station CLI

Building Agents

Station Lattice

Deployment

Advanced

Prerequisites

Step 1: Install Station

Step 2: Initialize with Your AI Provider

Git-Backed Workspace (Optional)

Step 3: Start Jaeger (Tracing)

Step 4: Connect Your MCP Client

Step 5: Start Using Station

Step 6: Interactive Hands-On Tutorial (Optional)

Next Steps

Create Agents

Add MCP Tools

Multi-Agent Teams

GitOps Workflow

​Prerequisites

​Step 1: Install Station

​Step 2: Initialize with Your AI Provider

​Git-Backed Workspace (Optional)

​Step 3: Start Jaeger (Tracing)

​Step 4: Connect Your MCP Client

​Step 5: Start Using Station

​Step 6: Interactive Hands-On Tutorial (Optional)

​Next Steps

Create Agents

Add MCP Tools

Multi-Agent Teams

GitOps Workflow

Prerequisites

Step 1: Install Station

Step 2: Initialize with Your AI Provider

Git-Backed Workspace (Optional)

Step 3: Start Jaeger (Tracing)

Step 4: Connect Your MCP Client

Step 5: Start Using Station

Step 6: Interactive Hands-On Tutorial (Optional)

Next Steps