• LOGISTICS
  • CONSTRAINTS
  • TIMING
  • HUMAN

How to optimize delivery routes with your AI

Connect GraphHopper once to let your agent handle the math for your fleet. It manages vehicle capacities and time windows so you don't have to.

Ask AI about this page

Short answer

How can I use AI to plan my delivery routes?

Your agent uses GraphHopper to calculate the best paths for your fleet while respecting vehicle limits and customer time windows. You get optimized routes that fit your specific constraints. Here is the breakdown of how it works.

The results of your optimization.

Where your routes land.

Once the agent finishes the math, you get these specific outcomes.

LOGISTICS

Optimized stop sequences

The AI provides the exact order of stops for every vehicle. You get a logical path that minimizes travel distance.

CONSTRAINTS

Capacity-aware planning

The agent ensures no vehicle is overloaded. It matches your cargo requirements to the specific limits of each truck.

TIMING

Time window compliance

Your routes respect customer availability. The AI schedules stops so drivers arrive when they are supposed to.

HUMAN

Manual route review

The AI handles the heavy computation, but you decide if a route needs a human tweak. You retain final control over the driver's schedule.

The workflow

What your AI does when the data arrives.

The agent handles the heavy lifting of solving the math and waiting for the solution.

  1. Submit constraints

    Your agent sends your fleet data, stop locations, and time windows to the optimizer.

    submit_vrp_optimizer

  2. Monitor progress

    The agent tracks the status of the calculation while the engine works through the permutations.

    poll_vrp_solution

  3. Retrieve routes

    Once the math is done, the agent pulls the completed route data for your review.

    poll_vrp_solution

  4. Verify constraints

    The agent checks the final solution against your original vehicle capacities and time windows.

    poll_vrp_solution

Try it

Copy these to start.

Use these prompts to kick off your first routing task.

Starting points

Replace the bracketed info with your actual fleet details and stop addresses.

GraphHopper Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_cQUPJxjf4FYe5KOaZuMFakr1XD1twCbw4cSXR3BG/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — GraphHopper capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "graphhopper-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_cQUPJxjf4FYe5KOaZuMFakr1XD1twCbw4cSXR3BG/mcp"
    }
  }
}
Copy into chat04

  • Optimize a route for 5 vans with a 500kg capacity each, using these stops: [list addresses].

  • Find the best delivery sequence for these 10 locations, making sure to respect the 2pm to 4pm time window.

  • Calculate a route for my delivery fleet based on this CSV of addresses and vehicle limits.

  • Solve a vehicle routing problem for these stops while ensuring no truck exceeds its weight limit.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect GraphHopper once, then ask.

You only need to link your account once. Your credentials stay encrypted, and you can immediately start asking your agent to solve routes.

Connect GraphHopper to your AI

FAQ

How the routing task behaves

  • 01

    Can the AI change my vehicle capacities?

    No. The AI uses the capacities you provide to calculate the routes, but it cannot modify your actual fleet data.

  • 02

    Does the AI automatically send routes to my drivers?

    No. The AI generates the optimized routes, but you must decide how to distribute that information to your team.

  • 03

    Can I include time windows for every stop?

    Yes. You can specify time windows for each location to ensure the AI plans around customer availability.

  • 04

    What happens if a vehicle is too small for a stop?

    The optimizer will attempt to find a valid solution, but if the constraints are impossible to meet, the calculation will reflect that.

  • 05

    Can the AI handle real-time traffic updates?

    The AI uses the data you submit to the optimizer. It does not independently pull live traffic feeds unless that data is included in your request.

  • More questions about GraphHopper? The Connector page answers them. See everything the GraphHopper Connector can do

Connect GraphHopper to Claude, Cursor, ChatGPT & more