Terminal49 MCP Server (TypeScript)
Vercel-native Model Context Protocol server for Terminal49's API, built with TypeScript and the official MCP SDK.
π Quick Deploy to Vercel

- Click "Deploy" above
- Add environment variable:
T49_API_TOKEN=your_token_here
- Deploy!
- Your MCP server will be available at:
https://your-deployment.vercel.app/api/mcp
π¦ What's Included
| Tool | Description | Key Features |
|---|
search_container | Search by container#, BL, booking, or reference | Fast fuzzy search |
track_container | Create tracking request and get container data | SCAC autocomplete β¨ |
get_container | Get detailed container info with flexible data loading | Progressive loading |
get_shipment_details | Get shipment routing, BOL, containers, ports | Full shipment context |
get_container_transport_events | Get full event timeline for a container | Milestone history |
get_supported_shipping_lines | List 40+ major carriers with SCAC codes | Filterable by name/code |
get_container_route | Get multi-leg routing with vessels and ETAs | Premium feature |
list_shipments | List shipments with filters and pagination | Fleet-level visibility |
list_containers | List containers with filters and pagination | Returns ResourceLinks β¨ |
list_tracking_requests | List tracking requests and statuses | Audit and monitoring |
π― Prompts (3 Workflows)
| Prompt | Description | Use Case |
|---|
track-shipment | Track container with optional carrier | Quick tracking start (SCAC autocomplete β¨) |
check-demurrage | Analyze demurrage/detention risk | LFD calculations |
analyze-delays | Identify delays and root causes | Timeline analysis |
The track-shipment prompt's carrier argument supports MCP completions (completion/complete): suggestions are sourced live from get_supported_shipping_lines, filtered by what the user has typed, and returned as SCAC codes.
π Resources
- β
terminal49://docs/milestone-glossary - Complete milestone reference guide
- β
terminal49://docs/mcp-query-guidance - Internal tool-routing hints
- β
terminal49://container/{id} - Dynamic container data access (also the target of list_containers ResourceLinks)
π§ Server Instructions
The server advertises MCP instructions (a server-level operating guide) at initialize time: it explains the ocean container/shipment tracking domain, key vocabulary (SCAC, BOL/booking, POL/POD, LFD, demurrage, holds), the read tools vs the single write tool (track_container), and the canonical tool-chaining order.
π ResourceLinks (context reduction)
list_containers returns MCP resource_link content blocks β one per container row β that point at the registered terminal49://container/{id} resource. Clients can render the compact list and resolve full per-container detail on demand via resources/read, instead of paying for every container's full payload up front.
π Content Audience Annotations
Tool results separate the human-readable answer from agent-steering metadata. The steering block (presentation guidance + suggested follow-up tools, derived from the _response_contract) is tagged with annotations: { audience: ['assistant'] } so spec-aware clients can hide it from end users, while the answer block stays user-visible.
β¨ Current Features (v1.0.0 - Phase 1 & 2.1 Complete)
β
Modern McpServer API
- High-level
registerTool(), registerPrompt(), registerResource() patterns
- Type-safe Zod schemas for all tool inputs
- Cleaner, maintainable code (71% code reduction in HTTP handler)
- MCP SDK: @modelcontextprotocol/sdk ^1.29.0
- Terminal49 SDK: @terminal49/sdk 0.2.0
β
Production Transport Support
- HTTP (streamable):
POST /api/mcp - stateless, JSON responses
- SSE was removed from the hosted deployment path in favor of Streamable HTTP transport.
β
Sentry MCP Monitoring
- Optional instrumentation with
@sentry/node ^10.55.0
- Captures MCP connections, tool calls, resources, prompts, performance spans, and errors when
SENTRY_DSN is set
- Tool input/output recording is disabled by default; enable it only after reviewing data handling requirements
β
3 Workflow Prompts
track-shipment: Quick container tracking with optional carrier
check-demurrage: Demurrage/detention risk analysis
analyze-delays: Journey delay identification and root cause
β
MCP Spec Adherence
- Server instructions: server-level operating guide advertised at initialize
- SCAC code completions:
completion/complete on the track-shipment prompt's carrier arg, sourced from get_supported_shipping_lines
- ResourceLinks:
list_containers rows link to the terminal49://container/{id} resource
- Content audience annotations: steering metadata tagged
audience: ['assistant']
π§ Deferred (future RFC β needs a stateful transport)
- Resource subscriptions, progress notifications, server logging, elicitation, and sampling all require a stateful (non-stateless-HTTP) transport and are out of scope here.
- Shipment ResourceLinks await a dedicated
terminal49://shipment/{id} resource template (only the container template is currently registered).
ποΈ Architecture
/api/mcp.ts # Vercel serverless function (HTTP)
/packages/mcp/
βββ src/
β βββ server.ts # MCP server (stdio)
β βββ index.ts # Stdio entry point
β βββ tools/ # MCP tools
β βββ resources/ # MCP resources
βββ package.json
MCP uses published @terminal49/sdk by default, with optional local override for contributors.
Transport:
- HTTP: Vercel serverless function at
/api/mcp (for hosted use)
- stdio: Local binary for Claude Desktop (run via
npm run mcp:stdio)
Store submission
The public connector URL is https://mcp.terminal49.com. Store assets and
submission metadata are checked in at the repository root:
chatgpt-app-submission.json β locked ChatGPT listing copy and review cases
claude-connector-submission.json β values to enter in Claude's submission portal
server.json β official MCP Registry metadata used for Copilot discovery
public/store-icons/terminal49-{light,dark}.png β 512Γ512 brand icons
Verify the domain for ChatGPT
OpenAI generates a unique domain-verification token during submission. Add that
exact value to the existing MCP Vercel project:
vercel env add OPENAI_APPS_CHALLENGE
After the project redeploys, verify that the well-known endpoint returns only
the token you pasted:
curl --fail --silent \
https://mcp.terminal49.com/.well-known/openai-apps-challenge
Do not commit the token. The endpoint returns an empty 404 response while
OPENAI_APPS_CHALLENGE is unset. Submit the connector and the values in
chatgpt-app-submission.json through the
OpenAI plugin submission flow.
Submit to Claude
Use the Claude Connectors Directory portal
and enter the values in claude-connector-submission.json. Upload the light
icon from public/store-icons/terminal49-light.png; the dark variant is
available for clients that support theme-specific assets.
Publish for Copilot discovery
GitHub's Copilot registry is a curated downstream discovery surface. Publish
server.json to the official MCP Registry to make Terminal49 eligible for that
surface:
mcp-publisher validate server.json
mcp-publisher login github
mcp-publisher publish server.json
The publisher must authenticate as an owner of the Terminal49 GitHub
organization because the registry name uses its io.github.Terminal49
namespace.
π οΈ Local Development
Prerequisites
Setup
cd packages/mcp
npm install
T49_SDK_SOURCE=published npm run sdk:setup
cp .env.example .env
Use a local SDK build during MCP development:
cd packages/mcp
T49_SDK_SOURCE=local npm run sdk:setup
Run Locally
npm run mcp:stdio
npm run dev
Test the API
echo '{"jsonrpc":"2.0","method":"tools/list","id":1}' | npm run mcp:stdio
echo '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"get_container","arguments":{"id":"123e4567-e89b-12d3-a456-426614174000"}},"id":2}' | npm run mcp:stdio
π Using with Vercel Deployment
Deploy
npm i -g vercel
vercel
vercel env add T49_API_TOKEN
Once deployed, your MCP server will be at: https://your-deployment.vercel.app/api/mcp
For Claude Desktop or other MCP clients:
{
"mcpServers": {
"terminal49": {
"url": "https://your-deployment.vercel.app/api/mcp",
"headers": {
"Authorization": "Token your_api_token_here"
}
}
}
}
For Cursor IDE:
{
"mcp": {
"servers": {
"terminal49": {
"url": "https://your-deployment.vercel.app/api/mcp",
"headers": {
"Authorization": "Token your_api_token_here"
}
}
}
}
}
π§ API Reference
HTTP Endpoint
URL: POST /api/mcp
Headers:
Authorization: Token your_api_token_here
Content-Type: application/json
Request (JSON-RPC):
{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "get_container",
"arguments": {
"id": "123e4567-e89b-12d3-a456-426614174000"
}
},
"id": 1
}
Response:
{
"jsonrpc": "2.0",
"result": {
"content": [
{
"type": "text",
"text": "{\"id\":\"...\",\"container_number\":\"...\", ...}"
}
]
},
"id": 1
}
Available Methods
| Method | Description |
|---|
initialize | Initialize MCP connection |
tools/list | List available tools |
tools/call | Execute a tool |
resources/list | List available resources |
resources/read | Read a resource |
π Authentication
For Vercel Deployment (HTTP)
Set as environment variable in Vercel dashboard:
T49_API_TOKEN=your_token_here
Or include in request headers:
Authorization: Token your_token_here
Token is the preferred scheme. Bearer your_token_here is also accepted for backward compatibility.
For Local stdio
Set in your environment:
export T49_API_TOKEN=your_token_here
π§ͺ Testing
npm test
npm run type-check
npm run lint
π Environment Variables
| Variable | Required | Default | Description |
|---|
T49_API_TOKEN | β
Yes | - | Terminal49 API token |
T49_API_BASE_URL | No | https://api.terminal49.com/v2 | API base URL |
OPENAI_APPS_CHALLENGE | Only for ChatGPT submission | - | Exact domain-verification token issued by the OpenAI submission portal |
NODE_ENV | No | development | Environment |
LOG_LEVEL | No | info | Logging level |
REDACT_LOGS | No | true | Redact tokens in logs |
SENTRY_ENABLED | No | true | Enables or disables Sentry when a DSN is configured |
SENTRY_DSN | No | - | Enables Sentry MCP Monitoring when set |
SENTRY_ENVIRONMENT | No | NODE_ENV | Sentry environment name |
SENTRY_RELEASE | No | VERCEL_GIT_COMMIT_SHA | Sentry release identifier |
SENTRY_TRACES_SAMPLE_RATE | No | 1.0 | Trace sampling rate from 0 to 1 |
SENTRY_MCP_RECORD_INPUTS | No | false | Record MCP tool/prompt inputs in Sentry |
SENTRY_MCP_RECORD_OUTPUTS | No | false | Record MCP tool/prompt outputs in Sentry |
SENTRY_SEND_DEFAULT_PII | No | false | Enables Sentry default PII behavior |
Only enable SENTRY_MCP_RECORD_INPUTS or SENTRY_MCP_RECORD_OUTPUTS after confirming that your Sentry project is approved to store shipment identifiers, references, and customer data.
Credential headers (Authorization, cookies, and any header whose name contains auth, token, secret, cookie, session, api-key, password, or signature) and request cookies are removed from every error and transaction event before it is sent, regardless of SENTRY_SEND_DEFAULT_PII.
π Ruby vs TypeScript
This repo includes two implementations:
| Feature | Ruby (/mcp) | TypeScript (/packages/mcp + /api) |
|---|
| Deployment | Railway, Fly.io, Heroku | β
Vercel (native) |
| HTTP Transport | Rack/Puma | β
Vercel Serverless |
| stdio Transport | β
Yes | β
Yes |
| Status | Complete | Complete |
| Use Case | Standalone servers | Vercel deployments |
Recommendation: Use TypeScript for Vercel deployments (zero-config, auto-scaling).
π¦ Vercel Configuration
The project includes vercel.json for optimal Vercel deployment:
{
"functions": {
"api/mcp.ts": {
"runtime": "nodejs20.x",
"maxDuration": 30,
"memory": 1024
}
}
}
Configuration Notes
- Runtime: Node.js 20.x
- Max Duration: 30 seconds (adjustable for Pro/Enterprise)
- Memory: 1024 MB
- CORS: Enabled for all origins (
Access-Control-Allow-Origin: *)
π Troubleshooting
"T49_API_TOKEN is required" error
Solution: Set environment variable in Vercel dashboard or locally:
vercel env add T49_API_TOKEN
"Method not allowed" error
Solution: Ensure you're using POST method, not GET:
curl -X POST https://your-deployment.vercel.app/api/mcp \
-H "Authorization: Token your_token" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/list","id":1}'
CORS errors in browser
Solution: CORS is configured in vercel.json. If issues persist, check Vercel deployment logs:
Timeout errors
Solution: Increase maxDuration in vercel.json (requires Vercel Pro/Enterprise):
{
"functions": {
"api/mcp.ts": {
"maxDuration": 60
}
}
}
π Documentation
π€ Contributing
- Fork the repo
- Create a feature branch:
git checkout -b feature/my-tool
- Make changes in
/packages/mcp/src/
- Add tests
- Run type check:
npm run type-check
- Submit PR
π License
Copyright 2024 Terminal49. All rights reserved.
π Support
Built with MCP TypeScript SDK π