ILP Drone Delivery

Enables LLMs to plan drone deliveries, check availability, and visualize routes via natural language against the ILP Drone Delivery system.

javascript

0

GitHub Stars

javascript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "rheabose-ilp-mcp-server": {
      "command": "node",
      "args": [
        "/Users/rheabose/ilp-mcp-server/server.js"
      ]
    }
  }
}

This MCP server lets you conversely speak to the ILP Drone Delivery System. You can ask an AI to plan deliveries, check which drones are available, and visualize routes using natural language instead of manual API calls. It bridges your language model with real drone data and flight planning, making complex planning fast and intuitive.

How to use

You interact with the ILP Drone Delivery MCP Server through a client that speaks the MCP protocol. You can ask for available drones, plan deliveries with specified weight and temperature requirements, check drone availability for a given scenario, and generate map visualizations of routes. Use natural language prompts to perform multi-step tasks such as planning multiple deliveries and visualizing routes.

How to install

Prerequisites you need before installing and running the MCP server:

• Node.js 18+ installed

• ILP CW2 Service running on http://localhost:8080

• Claude Desktop installed for LLM integration OR you can perform manual testing without Claude

cd ilp-mcp-server

# Install dependencies
npm install

# Make server executable
chmod +x server.js

# Link globally (for Claude Desktop)
npm link

Start the ILP CW2 service and run the MCP server

Start the ILP CW2 service, then run the MCP server. This ensures the MCP server can connect to the drone data feed and perform planning.

cd ILPCW2
java -jar target/*.jar app.jar

Verify the ILP service is running:

curl http://localhost:8080/api/v1/dronesWithCooling/false

Test the MCP Server

Run the test suite to verify the MCP server can connect to the ILP service and perform core actions.

cd ilp-mcp-server
npm test

Claude Desktop configuration

If you are using Claude Desktop for LLM integration, configure the MCP server as shown.

{
  "mcpServers": {
    "ilp-drone": {
      "command": "node",
      "args": ["/Users/rheabose/ilp-mcp-server/server.js"]
    }
  }
}

Available tools

list_available_drones

Retrieve all drones with capabilities, with optional filtering by cooling or other features.

get_drone_details

Fetch detailed information for a specific drone, including capacity and features.

plan_delivery

Plan a single delivery with cost estimates, required capacity, and route details.

check_drone_availability

Identify drones that can meet specific delivery requirements such as capacity and temperature needs.

get_delivery_geojson

Generate GeoJSON data for map visualization of planned routes.

plan_multiple_deliveries

Plan multi-drone delivery routes across several locations.