Frequently Asked Questions (FAQ) about the Data Engineering Tutor MCP Server

Q: What is the Data Engineering Tutor MCP Server?

A: It’s a Model Context Protocol (MCP) server that acts as a personalized tutor for data engineering concepts. It provides tailored updates about data engineering concepts, patterns, and technologies to a connected AI client.

Q: What is MCP?

A: MCP stands for Model Context Protocol. It’s an open protocol that standardizes how applications provide context to Language Models (LLMs). In this case, it allows the server to communicate information about data engineering to an AI client.

Q: What are the prerequisites for running this server?

A: You need Node.js (v18 or later), npm (or a similar package manager), an AI client capable of connecting to an MCP server (like Cursor or Claude), and an OpenRouter API key.

Q: Where do I get an OpenRouter API key?

A: You can obtain a key from OpenRouter.

Q: How do I configure the server with Cursor?

A: Go to Cursor Settings > MCP > Add new global MCP server. Then, paste the provided JSON configuration, ensuring the path to build/index.js is correct.

Q: What if Cursor isn’t using the server’s prompt automatically?

A: You can create a Cursor Project Rule to explicitly provide the guidance to Cursor. Follow the instructions in the ‘Using with Cursor’ section of the documentation.

Q: What resources does the server provide?

A: The server provides a resource called data_engineering_knowledge_memory, which stores a JSON object mapping known data engineering concepts to boolean flags (true if known, false if unknown).

Q: What tools are available on the server?

A: The server offers the following tools: * de_tutor_read_memory: Reads the current known concepts from the JSON file. * de_tutor_write_memory: Updates the JSON file to mark a concept as known or unknown. * de_tutor_get_updates: Uses your OpenRouter API key to query Perplexity for recent data engineering news.

Q: How does the server use my OpenRouter API key?

A: The de_tutor_get_updates tool uses your API key to access the Perplexity API and fetch the latest data engineering news and articles.

Q: Where is my knowledge stored?

A: Your knowledge is stored in a JSON file located at data/data-engineering-knowledge.json.

Q: Can I use a database instead of a JSON file for storing knowledge?

A: Yes, you can modify the server to use a database for more robust storage. The current implementation uses a JSON file for simplicity.

Q: How do I debug the server?

A: You can use the MCP Inspector (npx @modelcontextprotocol/inspector node ./build/index.js) to see the raw message flow between the server and the client. Ensure that your OpenRouter API key is set in your environment.

Q: Can I contribute to this project?

A: Yes, if you find any bugs or have suggestions for improvements, feel free to open an issue on the repository.

Q: How does this relate to the UBOS platform?

A: This MCP Server is an asset that can be used within the UBOS full-stack AI Agent Development Platform. UBOS helps you orchestrate AI Agents, connect them with your enterprise data, and build custom AI Agents with your LLM model and Multi-Agent Systems.