MCP Server

Provides AI assistants with direct access to Mapbox developer APIs and documentation.

Remote serverstreamable-http

What is the MCP MCP server?

MCP MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. Provides AI assistants with direct access to Mapbox developer APIs and documentation.

What you get

A Model Context Protocol (MCP) server that provides AI assistants with direct access to Mapbox developer APIs. This server enables AI models to interact with Mapbox services, helping developers build Mapbox applications more efficiently.

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

What the assistant can call

Once MCP is connected, these are the calls the assistant has available:

  • Input — limit (optional - max number of styles), start (optional - pagination token)
  • Returns — Array of style metadata with optional pagination info
  • Note — This tool automatically fetches the first available public token from your account for the preview URL. Requires at least one public token with
  • ListStylesTool — Requires styles:list scope
  • CreateStyleTool — Requires styles:write scope
  • RetrieveStyleTool — Requires styles:download scope
  • UpdateStyleTool — Requires styles:write scope
  • DeleteStyleTool — Requires styles:write scope
  • PreviewStyleTool — Requires tokens:read scope (to list tokens) and at least one public token with styles:read scope
  • compare_styles_tool — Compares two Mapbox styles and reports structural differences, including changes to layers, sources, and properties. This offline comparison tool

Configuration and credentials

You will need one environment variable: MAPBOX_ACCESS_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Before you rely on it

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch MCP.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp mcp server does with a few real requests.

Choosing this one

Plenty of planning and project tracking servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. MCP's toolset — Input, Returns, Note and 7 more — is a fair guide to whether it matches your workflow. It is maintained by mapbox; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
Inputlimit (optional - max number of styles), start (optional - pagination token)
ReturnsArray of style metadata with optional pagination info
NoteThis tool automatically fetches the first available public token from your account for the preview URL. Requires at least one public token with styles:read scope.
ListStylesToolRequires styles:list scope
CreateStyleToolRequires styles:write scope
RetrieveStyleToolRequires styles:download scope
UpdateStyleToolRequires styles:write scope
DeleteStyleToolRequires styles:write scope
PreviewStyleToolRequires tokens:read scope (to list tokens) and at least one public token with styles:read scope
compare_styles_toolCompares two Mapbox styles and reports structural differences, including changes to layers, sources, and properties. This offline comparison tool performs deep object comparison without requiring API access.

How to install the MCP MCP server

{
  "mcpServers": {
    "devkit": {
      "command": "npx",
      "args": ["-y", "@anthropic-ai/dxt"],
      "env": {
        "MAPBOX_ACCESS_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
MAPBOX_ACCESS_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use MCP to Input.
  • Use MCP to Returns.
  • Use MCP to Note.

Frequently asked questions

It connects MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 10 tools (Input, Returns, Note, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP directly.