opencage-geocoding-mcp
Provides forward and reverse geocoding using the OpenCage API, enabling conversion between addresses and geographic coordinates.
README
OpenCage Geocoding MCP Server
An MCP (Model Context Protocol) server that provides geocoding capabilities using the OpenCage geocoding API. This server allows you to convert between addresses and geographic coordinates.
PLEASE NOTE: the examples shown here are based on an integration with claude.ai's desktop client. MCP as a concept is supported by other services, but may require a slightly different configuration.
Features
- Forward Geocoding: Convert addresses or place names to coordinates (latitude/longitude)
- Reverse Geocoding: Convert coordinates to addresses
- API Status Monitoring: Check your API usage and rate limits (assuming your penCage account has hard limits).
Prerequisites
- Node.js (version 20 or higher)
- OpenCage geocoding API Key: Sign up on the OpenCage website to get a free-trial geocoding API key
Installation
-
Is MCP the right tool?
This MCP is the right tool for small amounts of geocoding, for example while manually prompting an LLM.
If however, you want to process larger volumes of data, for example CSV files full of address or coordinates, or connecting to database full of data, it is almost certainly both faster and more affordable to use our command line tools, or have the LLM write a script to call our API directly.
We offer a markdown-formatted opencage-geocoding-api SKILL file to train your AI on best practices for working with our geocoding API.
-
Clone the repository. Change into the repository directory
git clone git@github.com:OpenCageData/opencage-geocoding-mcp.git
# or
git clone https://github.com/OpenCageData/opencage-geocoding-mcp.git
cd opencage-geocoding-mcp
- Install dependencies:
npm install
This is enough to get the MCP working with Claude Desktop (see below)
If you want to develop the MCP and plan to query the MCP from the command line you will also need to:
- Set your OpenCage geocoding API key as an environment variable:
export OPENCAGE_API_KEY="your_opencage_geocoding_api_key_here"
- Build the project:
npm run build
Usage
Using within Claude Desktop
Add this configuration to your Claude Desktop config file
On a Mac the config file should be (~/Library/Application Support/Claude/claude_desktop_config.json), but you can also navigate to the file via the menu: Settings > Developer > Edit Config
{
"mcpServers": {
"opencage-geocoding": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/opencage-geocoding-mcp/build/index.js"],
"env": {
"OPENCAGE_API_KEY": "your_opencage_geocoding_api_key_here"
}
}
}
}
Available Tools
Note: the first time you run a command you will need to give Claude permission

1. geocode-forward
Convert an address or place name to coordinates and information about that location.
Parameters:
query(required): The address or place name to geocodecountrycode(optional): Restrict to country (ISO 3166-1 alpha-2 code)bounds(optional): Bounding box (min_lon,min_lat,max_lon,max_lat)language(optional): Language for results (e.g., 'en', 'de', 'fr')limit(optional): Max results (1-100, default 10)no_annotations(optional): Exclude location annotations
Example prompts
Prompt: "What are the coordinates of Trafalgar Square, London?"
Result: coordinates, timezone, local currency, etc
Prompt: "Where is Les Vans, France? Which Department is it in?"
Result: coordinates, and correct answer that Les Vans is in the Ardèche department
Prompt: "In welchem Bundesland liegt Weimar?"
Result: coordinates, and correct answer that Weimar is in Thüringen
2. geocode-reverse
Convert coordinates to an address and information about that location
Parameters:
latitude(required): Latitude coordinate (-90 to 90) in decimal formatlongitude(required): Longitude coordinate (-180 to 180) in decimal formatlanguage(optional): Language for resultsno_annotations(optional): Exclude location annotations
Example prompts
Prompt: "what is the address at 38.8976, -77.0365?"
Result: "1600 Pennsylvania Avenue NW, Washington, DC 20500, United States of America"
Prompt: "Which province are the coordinates 41.38700, 2.16995 in?"
Result: "Coordinates are in Barcelona in the province of Catalonia"
3. get-opencage-info
Check your current API usage and rate limits. NOTE: subscription customers do NOT have hard usage limits. See relevant documentation.
Parameters: None
Returns: Information about remaining requests, rate limits, and reset times.
Available Prompts
geocoding-assistant
A helpful assistant for geocoding tasks. Provides guidance on using the geocoding tools effectively.
Error Handling
The server includes comprehensive error handling:
- Invalid API keys
- Rate limit exceeded
- Network errors
- Invalid coordinates or addresses
- API service unavailable
Environment Variables
OPENCAGE_API_KEY: Your OpenCage geocoding API key (required)
Troubleshooting
- "API key required" error: Make sure the env var
OPENCAGE_API_KEYis set - "No results found": Try a more specific or different address format, see the OpenCage guide to query formatting
- Rate limit errors: Check your API usage with
get-api-statustool - Network errors: Verify internet connection or the public OpenCage status page
Relevant Links
-
OpenCage homepage - Get your geocoding API key
-
OpenCage API Documentation - Full OpenCage geocoding API reference
-
Model Context Protocol - Learn more about MCP
Who is OpenCage GmbH?
<a href="https://opencagedata.com"><img src="opencage_logo_300_150.png"></a>
We run a worldwide geocoding API and geosearch service based on open data. Learn more about us.
We also organize Geomob, a series of regular meetups for location based service creators, where we do our best to highlight geoinnovation. If you like geo stuff, you will probably enjoy the Geomob podcast.
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。