MCP Server Quickstart
This guide covers everything you need to connect Claude or Cursor to Terminal49’s container tracking data via MCP.Just want to get started fast? See MCP Overview for a 5-minute setup.
Prerequisites
Before you begin, make sure you have:Terminal49 Account
A Terminal49 account with API access
API Token
A
T49_API_TOKEN from the dashboardNode.js 18+
Required if running the MCP server locally
MCP Client
Claude Desktop or Cursor IDE
- MCP SDK:
@modelcontextprotocol/sdk ^1.26.0 - TypeScript SDK:
@terminal49/sdk - Runtime: Node.js 18+
Transports
Authentication: API token only (OAuth not required for this release).
Pass
Authorization: Bearer <T49_API_TOKEN> or Authorization: Token <T49_API_TOKEN>.Server falls back to
T49_API_TOKEN environment variable.
Configure your MCP client
Claude Desktop
- macOS
- Windows
- Linux
Edit
~/Library/Application Support/Claude/claude_desktop_config.json:Cursor IDE
Add to your Cursor settings:Local stdio (development)
For local development without a hosted server:Contributor mode: switch SDK source
Contributor mode: switch SDK source
Use published SDK by default:Use local SDK build during development:
Test your setup
Once configured, verify everything works:1
Restart your MCP client
Close and reopen Claude Desktop or Cursor to load the new config.
2
Ask Claude to list tools
“List the tools available in the Terminal49 MCP server.”Claude should respond with a list of 10 tools including
search_container, track_container, and list tools.3
Search for a test container
“Using the Terminal49 MCP server, search for container TCLU1234567 and summarize its status.”If configured correctly, Claude will call
search_container and return container details.4
Try a multi-step query
“Using Terminal49, find container CAIU1234567, check its demurrage risk, and tell me if I need to pick it up urgently.”Claude should chain multiple tools together to answer.
Need test container numbers? See Test Numbers for containers you can use during development.
Troubleshooting
Check MCP server logs
Check MCP server logs
If using the hosted server, check your Terminal49 dashboard for API logs.If running locally:
MCP capabilities
Tools
Prompts
Resources
For detailed examples and response formats, see MCP Overview → Tools Reference.
SDK usage
The TypeScript SDK provides the same capabilities as MCP tools, plus additional APIs not yet exposed via MCP.Response formats
Raw vs Mapped example
Raw vs Mapped example
Raw format:Mapped format:
Deployment
Vercel (production)
Thevercel.json configures the MCP server:
Environment variables
Testing locally
Related guides
- MCP Overview – Quick start and tools reference
- Rate Limiting – API limits (same for MCP)
- Test Numbers – Containers for testing
- Webhooks – Real-time updates
- API Data Sources – Data freshness and coverage