
RideWithGPS MCP Server
An AI-powered companion that provides access to the RideWithGPS API, allowing you to interact with cycling routes, trips, events, and user data through natural language.
README
RideWithGPS MCP Server
🚴 Dear Cyclists! Welcome to the RideWithGPS MCP Server—your AI-powered companion for managing your cycling adventures. If you like this project, please consider giving it a star, or better yet, becoming a contributor!
A Model Context Protocol (MCP) server that provides access to the RideWithGPS API, allowing you to interact with routes, trips, events, and user data.
Requirements
- Node.js: 18.0.0 or higher, 20.0.0 or newer recommanded (Download here)
Tools
This MCP server implements the following tools:
Route Retrival
- get_routes: Retrieve a list of routes owned by the user on RideWithGPS, ordered by updated_at descending
⚠️ Known Limitation: This tool can only access routes that you personally own. Routes that are shared with you but belong to other people will not appear in your results.
If you want to use a shared route with this server, please make a copy of it into your own RideWithGPS account first.
- get_route_details: Retrieve full details for a specific route including track points, course points, and points of interest. You can find the available list of information here
Trip & Activity Data
- get_trips: Retrieve a list of trips/activities owned by the user on RideWithGPS, ordered by updated_at descending
- get_trip_details: Retrieve full details for a specific trip including track points and performance data. You can find the available list of information here
User Profile
- get_current_user: Retrieve profile information for the user
Event Participation
- get_events: Retrieve a paginated list of events owned by the user, ordered by created_at descending
- get_event_details: Retrieve full details for a specific event including associated routes
Data Synchronization
- sync_user_data: Retrieve items (routes and/or trips) that the user has interacted with since a given datetime
Setup
In command line, clone this repository and change into its directory
git clone https://github.com/boezzz/ridewithgps-mcp.git
cd ridewithgps-mcp
Build the server app:
npm install
npm run build
Configure Claude Desktop:
You can install the Claude desktop app which supports MCP. Other commonly seen MCP clients should also work.
You can get your RideWithGPS API credentials from:
- API Key: Visit the developer settings page in your RideWithGPS account and create an API client
- Authentication Token: Select the API Client you created and go to its edit page. Click on 'Create new Auth Token' to obtain a new authentication token.
Then, open your Claude Desktop settings, go to Developers, and select 'Edit Config'. Alternatively, in your claude_desktop_config.json
file, add a new MCP server:
{
"mcpServers": {
"ridewithgps-mcp": {
"command": "node",
"args": ["/absolute/path/to/ridewithgps-mcp/build/index.js"],
"env": {
"RWGPS_API_KEY": "your_api_key_here",
"RWGPS_AUTH_TOKEN": "your_auth_token_here"
}
}
}
}
You can now launch Claude desktop app and ask it to interact with your RideWithGPS data.
Example queries:
- "Show me my recent routes"
- "Get details for the century route I created yesterday"
- "List my cycling trips from last month"
- "What events do I have coming up that I'll probably chicken out of?"
- "Show me my user profile so I can admire my optimistically low weight setting"
- "Sync my data since last week when I pretended that walk to the coffee shop was a training ride"
To use RideWithGPS MCP Server on other local MCP Clients, please follow the same steps.
API Coverage
This MCP server implements the main RideWithGPS API endpoints for individual users, excluding organization-specific features.
For complete API documentation, see: https://github.com/ridewithgps/developers
Development
Contributors welcome! To contribute to this project:
- Fork this repository to your own GitHub account.
- Clone your fork locally.
- Install dependencies:
npm install
- Make your changes to the TypeScript source files in
src/
- Build the project:
npm run build
- Test your changes using
npm run inspector
- Commit and push your changes to your fork.
- Submit a pull request to the main repository for review.
Development Roadmap
- Utilize OAuth for secure user authentication
- Deploy the MCP server to Smithery/Glama for distribution
- Incorporate geospatially-aware track points; currently, only the number is displayed
- Make pagination optional; it would also be helpful to return trips in descending order by departed time instead of updated time.
License
This project is licensed under the MIT License - see the LICENSE file for details.
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。