Frequently Asked Questions (FAQ) - CData MCP Server for Azure Table

Q: What is the CData MCP Server for Azure Table?

A: It’s a server that allows Large Language Models (LLMs) like Claude Desktop to query live Azure Table data using natural language. It acts as a bridge between the LLM and the Azure Table, translating natural language questions into a format that Azure Table understands.

Q: What is MCP?

A: MCP stands for Model Context Protocol. It’s an open protocol that standardizes how applications provide context to LLMs, enabling them to interact with external data sources and tools.

Q: What are the benefits of using the CData MCP Server for Azure Table?

A: Key benefits include enabling natural language queries for Azure Table data, accessing live data in real-time, simplifying data access for non-technical users, and improving the efficiency of data analysis.

Q: Is this a read/write MCP Server?

A: No, this project specifically builds a read-only MCP server. A full read/write MCP Server for Azure Table is available as a free beta on the CData website.

Q: What data sources are supported?

A: This specific MCP Server is designed for Azure Table. However, CData offers MCP Servers for dozens of other data sources, including databases, cloud applications, and more (see the complete list in the documentation).

Q: What is the CData JDBC Driver for Azure Table?

A: It’s a driver that connects to Azure Table by exposing its data as relational SQL models. The MCP Server uses this driver to interact with Azure Table.

Q: Do I need to know SQL to use this server?

A: No, you don’t need to know SQL. The server allows you to query Azure Table data using natural language. However, the underlying mechanism uses SQL queries, so understanding SQL can be beneficial for more advanced use cases.

Q: What is a .prp file?

A: A .prp file is a configuration file that contains the connection details for the JDBC driver. It includes information such as the driver path, JDBC URL, and table names.

Q: How do I configure Claude Desktop to use this server?

A: You need to modify the claude_desktop_config.json file to add a new MCP server entry, specifying the path to the Java executable, the MCP server JAR file, and the .prp file.

Q: I cannot see the CData MCP Server in Claude Desktop. What should I do?

A: Ensure that you have fully quit Claude Desktop and re-opened it. On Windows, use the Task Manager to close the application completely. On Mac, use the Activity Monitor.

Q: What is the license for this MCP server?

A: This MCP server is licensed under the MIT License, allowing you to use, modify, and distribute the software freely.

Q: Where can I find more help and support?

A: You can contact the CData Support Team or join the CData Community for assistance.

Q: Can I use this server with other AI clients besides Claude Desktop?

A: Yes, you can use this server with any AI client that supports the Model Context Protocol (MCP).

Q: Is the UBOS platform related to this MCP Server?

A: While this MCP server focuses on connecting Azure Table data to LLMs, UBOS is a full-stack AI Agent Development Platform. UBOS helps you orchestrate AI Agents, connect them with enterprise data, and build custom AI Agents with your own LLM models and Multi-Agent Systems.

Q: Where can I find the list of all supported sources by CData?

A: You can find the complete list of supported data sources in the documentation or on the CData website. The list includes databases, cloud applications, and more.