AI Integration & MCP

On this page

Connect your AI assistant to the Maptoolkit MCP server, and it can answer questions about the Maptoolkit APIs, call them, and write working map code for them. This works in Claude, ChatGPT, Gemini, Cursor, Windsurf, VS Code and any other app that supports remote MCP servers.

Model Context Protocol (MCP) is an open standard that lets AI assistants connect to external tools and APIs. Many apps call these connections connectors or apps.

Server address

https://mcp.maptoolkit.net

It is a remote server: there is nothing to install.

Add it to your assistant

Menus change as these apps are updated, and some features depend on your plan. If a step does not match what you see, check the app’s own help page, linked at the end of each section.

Claude

On Claude.ai or in the Claude desktop app:

Go to Settings → Connectors
Click Add custom connector
Enter the server URL: https://mcp.maptoolkit.net
Save. The connector is now available in all Claude clients (web, desktop, mobile)

On a Team or Enterprise plan, an owner may need to add the connector for the organization first.

→ Claude MCP setup guide

Claude Code

Run:

claude mcp add --transport http maptoolkit https://mcp.maptoolkit.net

Then type /mcp in Claude Code to check that the server is connected.

→ Claude Code MCP guide

ChatGPT

ChatGPT supports remote MCP servers on Plus, Pro, Team, and Enterprise plans.

Open ChatGPT and go to Settings → Connectors
Scroll to the bottom and click Advanced, then turn on Developer mode
Click Add connector and enter: https://mcp.maptoolkit.net

→ ChatGPT MCP setup guide

Gemini CLI

Open or create ~/.gemini/settings.json
Add the Maptoolkit server to the mcpServers section:

{
  "mcpServers": {
    "maptoolkit": {
      "url": "https://mcp.maptoolkit.net"
    }
  }
}

→ Gemini CLI MCP setup guide

Cursor

Open Cursor Settings (Cmd+, / Ctrl+,) and go to Features → MCP
Click + Add New MCP Server
Choose transport type streamable-http and enter: https://mcp.maptoolkit.net

You can also add it to .cursor/mcp.json in your project root or ~/.cursor/mcp.json for all projects:

{
  "mcpServers": {
    "maptoolkit": {
      "url": "https://mcp.maptoolkit.net"
    }
  }
}

→ Cursor MCP setup guide

Windsurf

Open Windsurf and click the MCP icon in the Cascade panel (or go to Settings → Cascade → MCP Servers)
Click Add MCP Server and enter: https://mcp.maptoolkit.net

You can also edit ~/.codeium/windsurf/mcp_config.json directly:

{
  "mcpServers": {
    "maptoolkit": {
      "url": "https://mcp.maptoolkit.net"
    }
  }
}

→ Windsurf MCP setup guide

VS Code

In VS Code with GitHub Copilot, run MCP: Add Server from the Command Palette, choose HTTP, and enter https://mcp.maptoolkit.net. You can also add it to .vscode/mcp.json in your project:

{
  "servers": {
    "maptoolkit": {
      "type": "http",
      "url": "https://mcp.maptoolkit.net"
    }
  }
}

→ VS Code MCP guide

Other apps

Any app that supports remote MCP servers can use Maptoolkit. Add a server with the address https://mcp.maptoolkit.net and the Streamable HTTP transport.

What the assistant can do

The server gives your assistant these tools:

Tool	What it does
`get_api_reference`	Returns the endpoints, parameters and response examples of a Maptoolkit API.
`get_integration_guide`	Returns a code template for a use case, such as an address search, a route planner or a store locator.
`get_types`	Returns TypeScript interfaces for the API responses.
`geocode`	Finds the coordinates of an address or place (Geocoding API).
`reverse_geocode`	Finds the address at a coordinate (Geocoding API).
`calculate_route`	Calculates a route with turn-by-turn directions (Routing API).
`calculate_isochrone`	Calculates the area you can reach within a travel time (Isochrone API).
`calculate_matrix`	Calculates travel times and distances between several origins and destinations.
`calculate_cycleway_route`	Routes from a start point to an end point along a given trail (Routing Enhancement API).
`enhance_route`	Adds elevation, surface, travel times and directions to a GPX or KML track (Route Enhancement API).
`get_elevation`	Returns the elevation of one or more coordinates (Elevation API).
`get_weather`	Returns the current weather and a forecast for a coordinate (Weather API).
`create_static_map`	Returns the URL of a map image with markers (Static Maps API).

You do not need to paste documentation into your prompt. Ask in your own words, and the assistant picks the tools it needs.

Using Prompts from the Documentation

Throughout this documentation you’ll find ready-to-use prompts alongside code examples. Each prompt is written to produce the shown result when used with an MCP-connected AI assistant.

Look for the Prompt tab in code examples - copy it directly into your AI tool and it will generate working map code, complete with your API key placeholder and the correct Maptoolkit endpoints.

Example: On Vector Tiles → MapLibre you’ll find prompts that produce a full MapLibre map with 3D terrain in one shot.

Example Prompts to Get Started

Once the MCP server is connected, try these:

Show me a full-page MapLibre map using Maptoolkit vector tiles
with the Summer style, centered on Vienna.

Create a routing example that finds the fastest route between
two coordinates and displays it on a Maptoolkit map.

Build a geocoding search box that shows results on an
interactive Maptoolkit map.