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.
What's New in v1.2.0
- NEW: Vessel name search: Search for vessels by name using
search_vessel_by_nametool- Query: "Where is the Ever Given?" → First searches by name, gets IMO, then tracks
Features
- 21 MCP Tools: 13 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 |
search_vessel_by_name |
Search vessels by name, returns IMO/MMSI | 1 |
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 search_vessel_by_name to find IMO, then track_vessel
"Track vessel IMO 9811000" (Ever Given)
→ Uses track_vessel directly (most efficient)
"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)
Tip: Using IMO (7 digits) or MMSI (9 digits) directly is most efficient. Use
search_vessel_by_namewhen you only know the vessel name (+1 credit).
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
Metadata
Release files for datadocked-mcp 1.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| datadocked_mcp-1.2.0.tar.gz | 13.0 kB | Without provenance | Details for datadocked_mcp-1.2.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| datadocked_mcp-1.2.0-py3-none-any.whl | Python 3 | none | any | Details for datadocked_mcp-1.2.0-py3-none-any.whl |
Total release size: 28.3 kB
Release files / datadocked_mcp-1.2.0.tar.gz
| Download URL | datadocked_mcp-1.2.0.tar.gz |
|---|---|
| Size | 13.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
cdbe8567f7c777df09b6a3f97a354a5fc3150c53dc0531122b8171bac58e3256
|
|
BLAKE2b-256 checksum How to use checksums |
710b7ad712fd512a8e61010bb279939fc341c9fc0d9c8c3ebf723152ef5e5e7e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.6
|
Release files / datadocked_mcp-1.2.0-py3-none-any.whl
| Download URL | datadocked_mcp-1.2.0-py3-none-any.whl |
|---|---|
| Size | 15.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1496f8ebbf88f02b47d96eb5ec00dfea2b679b52251853a07855b64782cd3bc8
|
|
BLAKE2b-256 checksum How to use checksums |
2031e9253bd485dd04dfa5b49745c5b65a76852cd4b559bc39f03568a810d9e0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.6
|
Security for datadocked-mcp 1.2.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.