Inavi MCP Server

MCP Server for iNavi Maps API - Geocoding, POI Search, Route Planning for Claude AI

Local serverstdioTypeScript

What is the Inavi MCP server?

Inavi MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. MCP Server for iNavi Maps API - Geocoding, POI Search, Route Planning for Claude AI.

What you get

AI 어시스턴트에 지도 인텔리전스를 부여하는 MCP (Model Context Protocol) 서버입니다.

What the assistant can call

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

  • list_api_specs — Browse available iNavi Maps API specifications by category
  • get_api_spec — Get the detailed specification of a specific API by operationId
  • list_map_examples — Browse available map visualization HTML examples
  • get_map_example — Get a specific map example's HTML template by id
  • search-place — 장소/주소 검색
  • search-geocoding — 지오코딩
  • search-spatial — 공간 검색
  • search-w3w — what3words
  • route-directions — 경로 탐색
  • route-optimization — 경유지 최적화
  • route-map-matching — 맵 매칭
  • route-matrix — 거리/시간 매트릭스

Setting it up

The server ships on npm as @inavi-maps/mcp-server, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Choosing this one

Plenty of developer tooling 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. Inavi's toolset — list_api_specs, get_api_spec, list_map_examples and 9 more — is a fair guide to whether it matches your workflow. It is maintained by inavi-systems; 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We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Inavi.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the inavi mcp server does with a few real requests.

Available tools

ToolWhat it does
list_api_specsBrowse available iNavi Maps API specifications by category.
get_api_specGet the detailed specification of a specific API by operationId.
list_map_examplesBrowse available map visualization HTML examples.
get_map_exampleGet a specific map example's HTML template by id.
search-place장소/주소 검색
search-geocoding지오코딩
search-spatial공간 검색
search-w3wwhat3words
route-directions경로 탐색
route-optimization경유지 최적화
route-map-matching맵 매칭
route-matrix거리/시간 매트릭스

How to install the Inavi MCP server

{
  "mcpServers": {
    "inavi": {
      "command": "npx",
      "args": ["-y", "@inavi-maps/mcp-server"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Inavi to list api specs.
  • Use Inavi to get api spec.
  • Use Inavi to list map examples.

Frequently asked questions

It connects Inavi to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (list_api_specs, get_api_spec, list_map_examples, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Inavi directly.