Unoffical Polestar 2 MCP
An MCP (Model Context Protocol) server that exposes Polestar 2 vehicle data to AI assistants like Claude. Query your car's battery status, vehicle info, and health data through natural conversation.
README
Polestar MCP Server
An MCP (Model Context Protocol) server that exposes Polestar 2 vehicle data to AI assistants like Claude. Query your car's battery status, vehicle info, and health data through natural conversation.
Disclaimer: This project uses an unofficial, reverse-engineered API and is not affiliated with or endorsed by Polestar. Use at your own risk. The API may change or break at any time.
Features
- Battery & Charging Status — Current charge level, charging state, estimated range, time to full charge
- Vehicle Information — Model details, VIN, registration number, software version, performance package
- Vehicle Health — Fluid levels, tire pressure warnings, service alerts
Prerequisites
- Python 3.10+
- A Polestar account with a registered vehicle
- Claude Desktop (or any MCP-compatible client)
Installation
# Clone the repository
git clone https://github.com/holger1411/polestar-mcp.git
cd polestar-mcp
# Create virtual environment
python -m venv .venv
source .venv/bin/activate
# Install dependencies
pip install -r requirements.txt
Configuration
Copy the example environment file and fill in your credentials:
cp .env.example .env
Edit .env with your Polestar account credentials:
POLESTAR_USERNAME=your-email@example.com
POLESTAR_PASSWORD=your-password
POLESTAR_VIN= # Optional: specify VIN if you have multiple vehicles
POLESTAR_LOG_LEVEL=INFO # Optional: DEBUG, INFO, WARNING, ERROR
Claude Desktop Setup
Add the following to your Claude Desktop configuration (claude_desktop_config.json):
{
"mcpServers": {
"polestar-mcp-server": {
"command": "/path/to/your/venv/bin/python",
"args": ["-m", "polestar_mcp_server"],
"env": {
"POLESTAR_USERNAME": "YOUR_EMAIL",
"POLESTAR_PASSWORD": "YOUR_PASSWORD",
"POLESTAR_VIN": "",
"POLESTAR_LOG_LEVEL": "INFO",
"PYTHONPATH": "/path/to/polestar-mcp/src"
}
}
}
}
Available Tools
| Tool | Description |
|---|---|
polestar_get_status |
Current battery level, charging state, range, and odometer reading |
polestar_get_vehicle_info |
Static vehicle details (model, VIN, registration, specs) |
polestar_get_health |
Vehicle health data (fluid levels, tire warnings, service alerts) |
Architecture
- Async-first — All API calls use
httpx.AsyncClientfor non-blocking I/O - OIDC/PKCE Authentication — Secure OAuth flow against Polestar's identity provider
- Smart Caching — TTL-based caching (battery: 3 min, health: 30 min, vehicle info: 24 h)
- Automatic Token Refresh — Handles expired tokens and re-authentication transparently
- Retry Logic — Handles rate limits (429) and transient server errors (5xx)
Dashboard
A standalone HTML dashboard (polestar-dashboard.html) is included as a visual prototype. It is a static mockup and does not connect to the API.
License
Acknowledgments
- Built with MCP (Model Context Protocol)
- API groundwork and reverse engineering by pypolestar/polestar_api — this project's authentication and GraphQL integration builds on their research
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。