Frequently Asked Questions (FAQ) about the CData MCP Server for Azure DevOps

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

A: The CData MCP Server for Azure DevOps allows LLMs (like Claude Desktop) to query live Azure DevOps data using natural language. It leverages the CData JDBC Driver to expose Azure DevOps data as SQL models, making it accessible to AI applications.

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

A: Key benefits include seamless integration with LLMs, natural language querying, live data access, simplified setup, and enhanced AI-powered reporting and project management.

Q: What is an MCP (Model Context Protocol) Server?

A: MCP is an open protocol that standardizes how applications provide context to LLMs. An MCP server acts as a bridge, allowing AI models to access and interact with external data sources and tools.

Q: What is the CData JDBC Driver?

A: The CData JDBC Driver connects to Azure DevOps by exposing data as relational SQL models. This enables standard SQL queries to retrieve and manipulate Azure DevOps data.

Q: Is the CData MCP Server read-only?

A: The described project builds a read-only MCP server. However, free (beta) read/write servers are available from CData.

Q: What is a .prp file and why is it needed?

A: The .prp file contains the connection configuration details for the JDBC driver, including the driver path, class name, JDBC URL, and any table prefixes. It is essential for configuring the connection to your Azure DevOps instance.

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

A: You need to modify the claude_desktop_config.json file to add a new entry for the MCP server, specifying the command and arguments required to run the server.

Q: What if I cannot see my CData MCP Server in Claude Desktop?

A: Ensure you have fully quit Claude Desktop (using Task Manager on Windows or Activity Monitor on Mac) and then reopen it.

Q: What tools are available through the MCP Server?

A: The main tools are {servername}_get_tables (to list available tables), {servername}_get_columns (to list columns for a table), and {servername}_run_query (to execute SQL queries).

Q: Where can I get help if I have trouble connecting to my data source?

A: Contact the CData Support Team for assistance.

Q: What license is the MCP server released under?

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

Q: How does UBOS enhance AI Agent development with the CData MCP Server?

A: UBOS provides a full-stack platform for orchestrating AI Agents, connecting them with enterprise data, building custom AI Agents with your LLM model, and creating Multi-Agent Systems, thus maximizing the value of data access via the CData MCP server.