Finding the fastest hospital in Dhaka with AI and Geoapify: MCP vs. OpenAPI

Description and use

The project shows how an AI agent and a CLI, using Geoapify MCP and OpenAPI, accurately identify the fastest hospital in Dhaka by travel time, correcting map‑based misconceptions.

Problem

In Dhaka, the hospital that looks closest on a map is often not the one you can reach first due to one‑way roads, canals, rivers and dense traffic.

Outcome

The AI agent and CLI consistently identified the fastest hospital by travel time, correcting common map‑based misconceptions and demonstrating the effectiveness of Geoapify’s MCP tools for emergency routing.

Workflow

• 1. Geocode the user’s address with geocode_address.
• 2. Search nearby hospitals with search_places.
• 3. Calculate travel times to up to 10 candidates using calculate_route_matrix with traffic=approximated.
• 4. Retrieve a detailed route with calculate_route (include_instructions:true).
• 5. Return the fastest hospital and route details to the user.

Evidence

In Dhaka, the hospital that looks closest on a map is often not the one you can reach first.

Source

The answer it gave: Emergency? Call 999. Fastest by car: AALOK HEALTHCARE (~2 min, 254 m)...

Source

Step 3 is the important one. Instead of sorting by straight‑line distance, we ask for travel times from one source to up to 10 candidates in a single request, and sort by time.

Source