This read-only MCP Server allows you to connect to Databricks data from Claude Desktop through CData JDBC Drivers. Free (beta) read/write servers available at
Overview
What is Databricks MCP Server by CData?
Databricks MCP Server by CData is a read-only Model Context Protocol (MCP) server that allows users to connect to Databricks data through CData JDBC Drivers, enabling natural language queries without the need for SQL.
How to use Databricks MCP Server?
To use the server, clone the repository, build the server, install the CData JDBC Driver, configure your connection, and create a configuration file for Claude Desktop to integrate the MCP server.
Key features of Databricks MCP Server?
- Read-only access to Databricks data via natural language queries.
- Simplified setup with CData JDBC Driver.
- Integration with Claude Desktop for AI-driven data queries.
Use cases of Databricks MCP Server?
- Querying live data from Databricks using natural language.
- Integrating with AI clients like Claude Desktop for data analysis.
- Accessing and managing data from various sources supported by Databricks.
FAQ from Databricks MCP Server?
- Can I write data using this server?
No, this is a read-only server. For write capabilities, consider the full CData MCP Server for Databricks.
- Is there a cost to use the server?
The server is currently in beta and is free to use.
- What kind of data sources can I connect to?
You can connect to various data sources supported by Databricks, including Salesforce, SQL databases, and more.