Frequently Asked Questions about MCP Server on UBOS

Q: What is MCP Server?

A: MCP (Model Context Protocol) Server acts as a bridge, allowing AI models to access and interact with external data sources and tools. It standardizes how applications provide context to Large Language Models (LLMs).

Q: What databases are compatible with MCP Server?

A: The provided guide primarily discusses PostgreSQL, but MCP Server also supports MySQL, MariaDB, and SQLite due to its use of SQLAlchemy under the hood. Theoretically, any database supported by SQLAlchemy can be used.

Q: Do I need Docker to use MCP Server?

A: While the guide uses Docker Compose for deploying a PostgreSQL database, Docker is not strictly required for MCP Server itself. However, using Docker simplifies the setup and ensures consistency.

Q: What is uv and why is it needed?

A: uv is a modern, high-performance Python package manager. It’s used to run the MCP Server application efficiently. The guide provides instructions for installing it if it’s not already installed on your system.

Q: How do I configure the database connection for MCP Server?

A: The database connection is configured through environment variables, specifically the DB_URL variable. This variable should contain the connection string for your database, including the database type, username, password, host, and port.

Q: Where do I find the MCP Server configuration file?

A: The location of the MCP Server configuration file depends on your specific setup. The guide provides a sample JSON configuration that you can save to a file and then reference in your MCP Server startup command.

Q: How do I launch the MCP Server?

A: The guide indicates that the MCP Server will automatically start each time Claude Desktop is launched, provided the configuration is in place. However, you may need to manually start the server using the uv command specified in the configuration if it doesn’t start automatically.

Q: What is Claude Desktop?

A: Claude Desktop is an AI assistant that can be connected to your database via MCP Server. It allows you to interact with your data using natural language queries.

Q: How does UBOS enhance MCP Server functionality?

A: UBOS is a full-stack AI Agent Development Platform that provides tools for orchestrating AI Agents, connecting them with enterprise data, building custom AI Agents with your LLM model and Multi-Agent Systems. UBOS makes it easier to build complex AI-powered applications that leverage MCP Server.

Q: What if I encounter issues during setup?

A: Refer to the relevant documentation for MCP Server, Claude Desktop, Docker Compose, and uv. You can also contact your support team for assistance.