Bouncie MCP Server
An MCP server that connects Bouncie OBD2 vehicle tracking data to AI assistants. It enables users to retrieve real-time vehicle stats, health diagnostics, and detailed trip history through the Bouncie API.
README
Bouncie MCP Server
An MCP (Model Context Protocol) server that exposes the Bouncie vehicle tracking API. Connect your Bouncie OBD2 device data to any MCP-compatible AI assistant.
Features
- Vehicle info — make, model, year, VIN, engine, nickname
- Live vehicle stats — GPS location, speed, fuel level, odometer, engine running status
- Vehicle health — battery status, check engine light (MIL), diagnostic trouble codes (DTCs)
- Trip history — distance, duration, speeds, fuel consumed, hard braking/acceleration, GPS traces
- User profile — authenticated user information
Prerequisites
- A Bouncie account with at least one connected device
- A Bouncie developer app — register at bouncie.dev
- Node.js 18+
Setup
1. Install
npm install
npm run build
2. Get Bouncie API credentials
- Go to bouncie.dev and create an app
- Note your Client ID and Client Secret
- Set a Redirect URI (e.g.
https://example.com/callback) - Under "Users & Devices", authorize your Bouncie account
- Copy the Authorization Code from the device's expanded view
3. Configure environment
Set these environment variables:
| Variable | Required | Description |
|---|---|---|
BOUNCIE_CLIENT_ID |
Yes | Your app's client ID |
BOUNCIE_CLIENT_SECRET |
Yes | Your app's client secret |
BOUNCIE_REDIRECT_URI |
Yes | Redirect URI used during app registration |
BOUNCIE_AUTH_CODE |
One of these | Authorization code (exchanged for token automatically) |
BOUNCIE_ACCESS_TOKEN |
One of these | Pre-obtained access token (skip OAuth exchange) |
4. Add to your MCP client
Claude Desktop / Claude Code
Add to your MCP settings (claude_desktop_config.json or .claude/settings.json):
{
"mcpServers": {
"bouncie": {
"command": "node",
"args": ["/path/to/bouncie-mcp/dist/index.js"],
"env": {
"BOUNCIE_CLIENT_ID": "your-client-id",
"BOUNCIE_CLIENT_SECRET": "your-client-secret",
"BOUNCIE_REDIRECT_URI": "https://example.com/callback",
"BOUNCIE_ACCESS_TOKEN": "your-access-token"
}
}
}
}
Tools
get_vehicles
List all vehicles on the account.
| Parameter | Type | Description |
|---|---|---|
vin |
string (optional) | Filter by VIN |
imei |
string (optional) | Filter by device IMEI |
Returns: Array of vehicles with model info, VIN, IMEI, nickname, and live stats (location, speed, fuel, odometer, engine status, battery, MIL/DTCs).
get_vehicle
Get a single vehicle by VIN or IMEI.
| Parameter | Type | Description |
|---|---|---|
vin |
string (optional) | Vehicle VIN |
imei |
string (optional) | Device IMEI |
At least one identifier is required.
get_trips
Get trip history for a vehicle.
| Parameter | Type | Description |
|---|---|---|
imei |
string | Device IMEI (required) |
starts_after |
string (optional) | ISO date — trips starting after this time |
ends_before |
string (optional) | ISO date — trips ending before this time |
gps_format |
"polyline" | "geojson" (optional) |
GPS data format (default: polyline) |
transaction_id |
string (optional) | Fetch a specific trip |
Note: The date window (
starts_aftertoends_before) must be no longer than 1 week. Defaults to the last 7 days if not specified.
Returns: Array of trips with distance, duration, average/max speed, fuel consumed, hard braking/acceleration counts, odometer readings, and GPS trace.
get_user
Get the authenticated user's profile.
No parameters.
Development
npm run dev # Run with tsx (hot reload)
npm run build # Compile TypeScript
npm test # Run tests
npm run test:watch # Watch mode
npm run lint # Type check
API Reference
This server wraps the Bouncie REST API v1:
- Base URL:
https://api.bouncie.dev/v1 - Auth:
https://auth.bouncie.com/oauth/token - Endpoints:
/vehicles,/trips,/user
Webhook Event Types
Bouncie also supports webhooks (not exposed via this MCP server, but documented here for reference):
| Event Type | Description |
|---|---|
connect |
Device plugged in |
disconnect |
Device unplugged |
battery |
Battery status change (normal/critical) |
mil |
Check engine light on/off with DTC codes |
tripStart |
Trip begins — includes odometer |
tripEnd |
Trip ends — includes odometer, fuel consumed |
tripMetrics |
Trip summary — distance, time, speeds, braking/acceleration |
tripData |
Real-time GPS breadcrumbs during trip |
License
MIT
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。