Frequently Asked Questions (FAQ)

Q: What is the Azure Cosmos DB MCP Server?

A: The Azure Cosmos DB MCP Server is a tool that allows Large Language Models (LLMs) like Claude to directly interact with your Azure Cosmos DB data using natural language. It acts as a translator between the AI model and the database.

Q: What is MCP?

A: MCP stands for Model Context Protocol. It’s an open protocol that standardizes how applications provide context to LLMs. The MCP server allows AI models to access and interact with external data sources and tools.

Q: What are the prerequisites for using the Azure Cosmos DB MCP Server?

A: You need Node.js 14 or higher, an Azure Cosmos DB NOSQL account (or the emulator), and Claude Desktop.

Q: How do I install the Azure Cosmos DB MCP Server?

A: First, install the dependencies using npm install. Then, build the project with npm run build. Finally, start the server from the dist folder using npm start.

Q: How do I configure Claude Desktop to use the MCP Server?

A: Open Claude Desktop, navigate to File -> Settings -> Developer -> Edit Config, and modify the claude_desktop_config file to include the path to your Azure Cosmos DB MCP server file and your Cosmos DB credentials.

Q: Can I use the MCP Server with other AI models besides Claude?

A: While the MCP Server is built to support any AI model, the current developer preview is accessible through Claude Desktop. Future versions may support other AI models.

Q: Is the Azure Cosmos DB MCP Server secure?

A: Yes, the MCP Server implements security measures to protect your data. Make sure to follow security best practices when configuring your Azure Cosmos DB account and the MCP Server.

Q: Where can I find more information about the Azure Cosmos DB MCP Server?

A: You can find more information, including detailed instructions and documentation, on the UBOS Asset Marketplace.

Q: What is UBOS?

A: UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. Our platform help you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model and Multi-Agent Systems.