APM Terminal Operations Intelligence
Provides natural language access to terminal operations data including vessel operations, yard inventory, gate activity, equipment performance, and delays. Enables executive queries for benchmarking, root cause analysis, and throughput patterns with interactive visualization and PDF reporting capabilities.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
APMT AI Operations Assistant
AI-powered terminal intelligence platform for APM Terminals. Ask questions about vessel operations, yard inventory, gate activity, and equipment performance using natural language. Powered by Claude (Anthropic).
Features
AI Chat
Natural language queries against live terminal database
31 specialized database tools (vessels, yard, gate, equipment, delays)
Smart follow-up suggestions after each response
Natural language date handling ("last week", "this month", "Q1")
Multi-step analysis for root cause questions
Conversation history (SQLite)
Visualization
Interactive charts (ApexCharts) — bar, line, pie, doughnut
Paginated tables and charts (10 items per page)
Terminal Overview — full dashboard in one query
Weekly comparison mode (moves, productivity, delays)
Reports
Expand to fullscreen modal
Export to PDF with charts (html2canvas + jsPDF)
Email report delivery (SMTP)
Response feedback (thumbs up/down)
Executive Queries (HQ)
CMPH vs target benchmarking
Best/worst vessel ranking
Delay root cause analysis
Delay breakdown by category
Gate throughput patterns
Berth utilization trends
Dwell time analysis
UX
KPI summary cards (auto-refresh)
Voice input with terminal vocabulary correction
Onboarding tour (driver.js)
Keyboard shortcuts (Ctrl+K, Ctrl+E, Ctrl+N)
Sound notification on response
Two-layer caching (query + response)
Admin health dashboard (/admin)
Maersk Headline font
Related MCP server: MySQL MCP Server Pro
Quick Start
Prerequisites
Node.js 20+
MySQL 8.0
Anthropic API key
Setup
# Install dependencies
npm install
# Copy and configure environment
cp .env.example .env
# Edit .env with your MySQL and Anthropic credentials
# Build
npm run build
# Start
npm startThe app will import the demo database on first run and start at http://localhost:3000.
Environment Variables
# MySQL
DB_HOST=localhost
DB_PORT=3306
DB_USER=root
DB_PASSWORD=root
DB_NAME=compass_db
# AI
ANTHROPIC_API_KEY=sk-ant-...
# CLAUDE_MODEL=claude-sonnet-4-20250514
# Server
CHAT_SERVER_PORT=3000
# Cache TTLs (minutes)
CACHE_TTL_STATIC=60
CACHE_TTL_SLOW=60
CACHE_TTL_LIVE=60
CACHE_TTL_RESPONSE=60
# Email (optional)
# SMTP_HOST=smtp.gmail.com
# SMTP_PORT=587
# SMTP_USER=your-email@gmail.com
# SMTP_PASS=your-app-passwordDocker
docker compose up -dOr deploy to Coolify — the MYSQL_DATABASE env var creates the DB automatically.
Project Structure
src/
chat-server.ts # Express server, Claude API, all endpoints
chat-history.ts # SQLite conversation history (sql.js)
database.ts # MySQL connection pool
init-database.ts # Auto-import demo data on first run
queries.ts # All SQL queries (50+)
public/
index.html # UI (Tailwind CSS, Lucide icons)
script.js # Frontend logic (charts, pagination, voice, etc.)
fonts/ # Maersk Headline webfont
demo_database.sql # Slim demo dataset (1.8MB, ~30 vessel visits)API Endpoints
Endpoint | Method | Description |
| POST | Chat with Claude (tool calling) |
| GET | Live KPI summary |
| GET/POST | List/create conversations |
| GET/DELETE | Get/delete conversation |
| POST | Submit response feedback |
| POST | Email a report |
| GET | Health check + cache stats |
| DELETE | Clear all caches |
| GET | Admin dashboard |
Keyboard Shortcuts
Shortcut | Action |
| Focus chat input |
| Export last response |
| New chat |
| Close modals |
| Show shortcuts |
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Query, explore, and manage your databases through natural conversation.
Ask questions in plain language, get answers from your business database. No SQL required.
Work with your database from AI tools: ask, export, approved changes, and scheduled jobs.
Ask business questions in plain English. Get instant answers from your database, no SQL needed.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables interaction with MySQL databases (including AWS RDS and cloud instances) through natural language. Supports database connections, query execution, schema inspection, and comprehensive database management operations.826 npm7MIT
- AlicenseBqualityDmaintenanceProvides comprehensive MySQL database operations including CRUD, performance optimization, health analysis, and anomaly detection. Supports multiple connection modes, OAuth2.0 authentication, and role-based permissions for database management through natural language.91MIT
- AlicenseNot gradedqualityDmaintenanceEnables natural language database operations on MySQL databases with AI integration, supporting CRUD operations, schema inspection, and audit logging with built-in security features including SQL injection protection and permission controls.798 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables comprehensive MySQL database management including CRUD operations, schema queries, and natural language to SQL conversion support through complete database structure analysis.798 npm2MIT