VanMoof MCP Server

The VanMoof MCP Server bridges the gap between AI assistants and the rich ecosystem of Van Moof’s rider data. By implementing the Model Context Protocol, it exposes a curated set of resources—bike details, city‑level ride statistics, rider preferences, and weekly ride summaries—to external agents. Developers can now query a user’s Van Moof account with natural language prompts, allowing AI assistants to deliver personalized insights without the need for custom API integrations.

At its core, the server provides a collection of high‑level tools that abstract away authentication and data transformation. For example, pulls the authenticated rider’s bike information, while returns a geo‑refined list of all cities where rides are tracked. These tools can be invoked directly from an AI prompt, enabling conversations such as “Give me my Van Moof bike details” or “Create a table of Dutch cities with ride metrics.” The server handles token management, rate limiting, and error handling internally, freeing developers from boilerplate code.

Key capabilities include:

• Contextual Ride Analytics: and provide aggregate metrics (total distance, average speed) for a user’s weekly rides.
• Geospatial Insights: and allow comparison between local and global rider activity.
• Preference Retrieval: exposes user‑specific settings, such as preferred city or ride goals.
• Customer Data Access: supplies bike model, frame number, and color information for personalized recommendations.

These features enable a range of real‑world scenarios. A cycling coach chatbot could analyze a rider’s weekly performance against city averages to suggest training adjustments. An itinerary assistant might recommend cities with high Van Moof activity for a cycling trip, complete with coordinates. A marketing team could surface global trends to tailor promotional campaigns.

Integration into AI workflows is straightforward: the server’s tools are registered as MCP resources, so any client that speaks the protocol—Claude, ChatGPT, or a custom assistant—can invoke them via natural language. The server returns structured JSON that the agent can parse, format, or embed in markdown tables, making it ideal for reporting and dashboard generation. Its unique advantage lies in the seamless blend of user‑specific data with broader city and world statistics, all delivered through a single, protocol‑compliant interface.