datadocked-mcp 1.1.0

MCP Server for DataDocked Maritime API - Real-time vessel tracking, port operations, and maritime intelligence

DataDocked MCP Server (Python)

MCP (Model Context Protocol) server for the DataDocked Maritime API. Enables AI assistants like Claude to access real-time vessel tracking, port operations, and maritime intelligence.

Features

• 20 MCP Tools: 12 basic single-endpoint tools + 8 compound multi-endpoint tools
• Pre-execution Credit Warnings: Know the cost before running operations
• Rich Formatted Output: Markdown tables and structured reports
• Async API Client: Non-blocking concurrent requests for compound tools

Installation

PyPI (Recommended)

pip install datadocked-mcp

From Source

git clone https://github.com/datadocked/mcp-server.git
cd mcp-server/datadocked-mcp-py
pip install -e .

Configuration

Environment Variables

# Required: Your DataDocked API key
export DATADOCKED_API_KEY="your_api_key_here"

# Optional: Disable credit cost warnings (default: true)
export DATADOCKED_SHOW_COST="false"

Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "datadocked": {
      "command": "datadocked-mcp",
      "env": {
        "DATADOCKED_API_KEY": "your_api_key_here"
      }
    }
  }
}

Or using uvx:

{
  "mcpServers": {
    "datadocked": {
      "command": "uvx",
      "args": ["datadocked-mcp"],
      "env": {
        "DATADOCKED_API_KEY": "your_api_key_here"
      }
    }
  }
}

Cursor / VS Code

Add to your MCP settings:

{
  "datadocked": {
    "command": "datadocked-mcp",
    "env": {
      "DATADOCKED_API_KEY": "your_api_key_here"
    }
  }
}

Available Tools

Basic Tools (Single-Endpoint)

Tool	Description	Credits
track_vessel	Real-time position, speed, course, ETA	1
track_vessels_bulk	Track up to 50 vessels	1/vessel
get_vessel_history	Historical positions (up to 2 years)	5/day
search_vessels_by_area	Find vessels in geographic region	10
get_vessel_details	Full vessel profile	5
get_vessel_specs	Dimensions, tonnage, capacity	3
get_vessel_engine	Engine specs, fuel type	3
get_vessel_management	Owner, operator, P&I club	3
get_port_calls	Port visit history	1
get_port_traffic	Port arrivals/departures	5
get_psc_inspections	PSC inspection records	3
get_vessel_weather	Weather at vessel location	2

Compound Tools (Multi-Endpoint)

Tool	Description	Credits
vessel_intelligence_report	Complete vessel dossier (6 endpoints)	~18
fleet_dashboard	Fleet status with vessel details	~3/vessel
voyage_analysis	Current voyage with context	~13
risk_assessment	Composite risk score	~12
area_intelligence	Region with full vessel profiles	10 + 5/vessel

Usage Examples

Natural Language Queries

"Where is the Ever Given right now?"
→ Uses track_vessel

"Show me all tankers near the Strait of Hormuz"
→ Uses search_vessels_by_area with vessel_type filter

"Give me a full intelligence report on vessel 9321483"
→ Uses vessel_intelligence_report (6 API calls combined)

"What's the risk profile of this vessel?"
→ Uses risk_assessment (4 API calls + analysis)

Credit Estimation

When enabled, each tool shows the estimated cost before execution:

--- Credit Estimate ---
Operation: Vessel Intelligence Report
Estimated Cost: 18 credits
Current Balance: 1,250 credits
To disable: set DATADOCKED_SHOW_COST=false
------------------------

Resources

The server also exposes MCP resources:

Resource URI	Description
datadocked://credits/balance	Current credit balance

Development

# Install in development mode
pip install -e ".[dev]"

# Run the server
python -m datadocked_mcp.server

# Or use the CLI
datadocked-mcp

Requirements

• Python 3.10+
• mcp >= 1.0.0
• httpx >= 0.25.0
• pydantic >= 2.0.0

API Reference

Full API documentation: https://docs.datadocked.com

License

MIT

Support

• Documentation: https://docs.datadocked.com
• Issues: https://github.com/datadocked/mcp-server/issues
• Website: https://datadocked.com