databricks-mcp-server-by-cdata
If you are the rightful owner of databricks-mcp-server-by-cdata and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
CData's Model Context Protocol (MCP) Server for Databricks is a read-only server that allows LLMs to query live data from Databricks using the CData JDBC Driver.
The CData MCP Server for Databricks is designed to facilitate the interaction between large language models (LLMs) and Databricks data. By leveraging the CData JDBC Driver, this server exposes Databricks data as relational SQL models, enabling LLMs to query live data without requiring SQL knowledge. This read-only server is ideal for users who need to access Databricks data in real-time through natural language queries. The server is built using Java and requires the CData JDBC Driver for Databricks to function. It is particularly useful for applications like Claude Desktop, where users can configure the server to retrieve data seamlessly.
Features
- Read-only access to Databricks data through MCP interface.
- Integration with CData JDBC Driver for Databricks.
- Natural language querying without SQL knowledge.
- Compatible with LLMs like Claude Desktop.
- Configurable connection settings for various data sources.
Tools
{servername}_get_tables
Get a list of available tables in the data source
{servername}_get_columns
Get a list of available columns in the table
{servername}_run_query
Execute SQL SELECT query
