What is an MCP Server?

An 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 LLMs.

What data sources can I connect to using this MCP Server?

You can connect to over 300 data sources, including SaaS applications, NoSQL databases, and more, through CData JDBC Drivers.

Is this MCP Server read-only?

Yes, this specific server builds a read-only MCP server. For full read, write, update, and delete capabilities, check out the free CData MCP Servers (beta) at https://www.cdata.com/solutions/mcp.

Do I need to know SQL to use this server?

No, you can use natural language to query data. The server translates your natural language questions into SQL queries.

How do I set up the MCP Server?

1. Clone the repository from GitHub.
2. Build the server using Maven.
3. Download and license a CData JDBC Driver.
4. Configure your connection to the data source.
5. Create a .prp configuration file.
6. Configure Claude Desktop with the new MCP server.
7. Run or refresh Claude Desktop.

What is UBOS?

UBOS is a full-stack AI Agent Development Platform that helps you orchestrate AI Agents, connect them with your enterprise data, and build custom AI Agents with your LLM model and Multi-Agent Systems.

Where can I find the CData JDBC Drivers?

You can download CData JDBC Drivers from https://www.cdata.com/jdbc.

What if I am having trouble connecting to a data source?

Contact the CData Support Team at https://www.cdata.com/support/submit.aspx.

What do I do if I can’t see the CData MCP Server in Claude Desktop?

Be sure that you have fully quit Claude Desktop (Windows: use the Task Manager, Mac: use the Activity Monitor) and then re-open it.

Where can I get support for using the MCP server?

Join the CData Community at https://community.cdata.com for assistance and feedback.