searoute_mcp

Table of Contents

• Overview
• Installation
• Quickstart
• Core Tools
• Example Prompts
• Running Your Server
• Contributing
• License
• References

---

Overview

searoute_mcp is a Model Context Protocol (MCP) server for maritime routing.
It integrates searoute-py with MCP, exposing tools that allow LLM clients (e.g. Claude Desktop) to:

• Compute oceangoing route distances (in nautical miles)
• Retrieve full oceangoing routes with waypoints (GeoJSON format)
• Compare against geodesic great-circle distances

All tools accept latitude, longitude as inputs for user friendliness, while internally converting to the required searoute format.

---

Installation

Clone the repository and install dependencies:

git clone https://github.com/ShippingIntel/searoute_mcp.git
cd searoute_mcp
python3 -m venv .venv
source .venv/bin/activate   # Linux/macOS
.venv\Scripts\activate      # Windows

pip install -r requirements.txt

Dependencies:

• mcp[python]>=0.1.0
• searoute>=1.4.3
• geopy>=2.4.1

---

Quickstart

Run the server locally:

python -m mcp_server.main

Install into Claude Desktop:

mcp install mcp_server/main.py

Test with the MCP Inspector:

mcp dev mcp_server/main.py

---

Core Tools

• compute_distance Shortest oceangoing route distance (nm) between two coordinates.

• compute_route Full oceangoing route (GeoJSON geometry + distance).

• compute_geodesic Great-circle (sphere) distance in nautical miles, ignoring land/sea constraints.

---

Example Prompts

All prompts use latitude, longitude ordering.

{
  "tool": "compute_distance",
  "arguments": {
    "start_lat": 47.6062,
    "start_lon": -122.3321,
    "end_lat": 35.6895,
    "end_lon": 139.6917
  }
}

{
  "tool": "compute_route",
  "arguments": {
    "start_lat": 40.7128,
    "start_lon": -74.0060,
    "end_lat": 48.8566,
    "end_lon": 2.3522
  }
}

{
  "tool": "compute_geodesic",
  "arguments": {
    "start_lat": 51.5072,
    "start_lon": -0.1276,
    "end_lat": -33.8688,
    "end_lon": 151.2093
  }
}

Examples:

• Seattle → Tokyo (oceangoing distance)