Frequently Asked Questions about UBOS Asset Marketplace: CData MCP Server for Azure Data Lake Storage

Q: What is an MCP Server? A: MCP (Model Context Protocol) 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 by providing a simplified interface.

Q: How does the CData MCP Server for Azure Data Lake Storage work? A: The CData MCP Server for Azure Data Lake Storage allows LLMs, like Claude, to query live data in Azure Data Lake Storage using natural language. It leverages CData JDBC Drivers to expose Azure Data Lake Storage data as relational SQL models, making it accessible through a simplified MCP interface.

Q: What are the benefits of using this MCP Server? A: Key benefits include:

• Natural language querying of Azure Data Lake Storage data.
• Real-time data access for AI agents.
• Simplified integration with LLMs.
• Enhanced data security.
• Increased efficiency in data analysis.
• Improved data-driven decision-making.

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 helps you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model, and create Multi-Agent Systems.

Q: How do I get started with the CData MCP Server on UBOS? A: To get started:

1. Acquire the CData MCP Server for Azure Data Lake Storage asset from the UBOS Asset Marketplace.
2. Configure the connection to your Azure Data Lake Storage instance following the asset documentation.
3. Configure Claude Desktop.
4. Deploy and test the MCP server within the UBOS platform.
5. Integrate the MCP server with your AI agents using UBOS orchestration tools.

Q: What data sources are supported by CData? A: CData supports connectivity to a vast array of data sources, including:

Access, Act CRM, Active Directory, Azure Data Lake Storage, BigQuery, Cassandra, DB2, Dynamics 365, Excel, Facebook, GitHub, Google Analytics, HubSpot, Jira, LinkedIn, Marketo, MongoDB, MySQL, NetSuite, OData, Oracle, PostgreSQL, Redshift, Salesforce, SAP, ServiceNow, SharePoint, Snowflake, SQL Server, and many more.

Q: Is this MCP Server read-only? A: The provided project builds a read-only MCP server. However, CData offers free (beta) read/write servers with simplified setup. Details can be found at https://www.cdata.com/solutions/mcp.

Q: Do I need a license for the CData JDBC Driver? A: Yes, you need to license the CData JDBC Driver. You can use a trial license by entering “TRIAL” during the licensing process, or you can enter your purchased license key.

Q: Where can I find support if I encounter issues? A: For issues connecting to your data source, contact the CData Support Team: https://www.cdata.com/support/submit.aspx. For problems using the MCP server or any other feedback, join the CData Community: https://community.cdata.com.

Q: What is the license for this MCP server? A: This MCP server is licensed under the MIT License. You are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. See the LICENSE file in the project repository for more details.