MapGO MCP
Provides geospatial tools for AI assistants to determine location hierarchy, border distance, coastline distance, and point-to-point distance using MapGO.
README
MapGO MCP Server
Give your AI assistant (Claude Desktop, Claude Code, Cursor, …) live geospatial tools powered by MapGO:
| Tool | What it answers |
|---|---|
mapgo_location_hierarchy |
"What country/region/municipality is this coordinate in?" |
mapgo_border_distance |
"How far is this point from the nearest country border?" |
mapgo_coastline_distance |
"How far is this point from the sea?" |
mapgo_point_distance |
"How far apart are these two points, and in which direction?" |
All coordinates are decimal degrees (latitude −90..90, longitude −180..180).
Requirements
- A MapGO account on a paid plan — tool calls count against your monthly request quota.
- An API key: go to mapgo.io/dashboard/api-keys,
click Generate, and copy the
mapgo_sk_...key (it is shown only once).
Install in Claude Desktop — one file, no terminal (recommended)
The easiest way. No Node install, no config files, no command line — Claude Desktop runs everything for you.
- Download
mapgo.mcpb(from mapgo.io, or from this repo). - Open Claude Desktop → the ☰ menu → Settings → Extensions.
- Drag
mapgo.mcpbonto the Extensions page (or double-click the file). - When prompted, paste your MapGO API Key (
mapgo_sk_...) into the box and click install / enable. - Ask Claude a location question — e.g. "How far is Paris from the coastline?"
That's it. The key is stored securely by your operating system; everything else is bundled inside the file.
The options below are for developer tools (Claude Code, Cursor) or for running from source. Most users only need the one-file install above.
Requirements for the developer / source options
- Node.js 18 or newer.
Install — run from source
Until the npm package is published, clone and build this repo once:
git clone https://github.com/Nomit83/mapgo_mcp.git
cd mapgo_mcp
npm install
npm run build
Then use node /full/path/to/mapgo_mcp/dist/index.js as the server command in the
configs below (in place of npx -y @mapgo/mcp-server). For example, for Claude Code:
claude mcp add mapgo --env MAPGO_API_KEY=mapgo_sk_YOUR_KEY_HERE -- node /full/path/to/mapgo_mcp/dist/index.js
Claude Desktop
Add this to claude_desktop_config.json (Settings → Developer → Edit Config),
then restart Claude Desktop:
{
"mcpServers": {
"mapgo": {
"command": "npx",
"args": ["-y", "@mapgo/mcp-server"],
"env": { "MAPGO_API_KEY": "mapgo_sk_YOUR_KEY_HERE" }
}
}
}
Claude Code
claude mcp add mapgo --env MAPGO_API_KEY=mapgo_sk_YOUR_KEY_HERE -- npx -y @mapgo/mcp-server
Cursor
Add to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):
{
"mcpServers": {
"mapgo": {
"command": "npx",
"args": ["-y", "@mapgo/mcp-server"],
"env": { "MAPGO_API_KEY": "mapgo_sk_YOUR_KEY_HERE" }
}
}
}
Try it
Ask your assistant:
"How far is Kraków from the coast, and which country border is nearest?"
Troubleshooting
- "Invalid or missing MapGO API key" — re-check the key in your config; generate a new one at mapgo.io/dashboard/api-keys if lost.
- "requires a paid plan" — API access (including MCP) is for paid plans.
- "Monthly MapGO quota exceeded" — each tool call uses 1 request from your plan's monthly quota; it resets on the 1st of the month.
Environment variables
| Variable | Required | Default | Purpose |
|---|---|---|---|
MAPGO_API_KEY |
yes | — | Your mapgo_sk_... API key |
MAPGO_API_BASE |
no | https://mapgo.io |
Override for local testing (http://localhost:3000) |
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。