databricks-mcp-server
If you are the rightful owner of databricks-mcp-server 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.
This is a Model Context Protocol (MCP) server for executing SQL queries against Databricks using the Statement Execution API.
The Databricks MCP Server is designed to facilitate the execution of SQL queries on Databricks through the Statement Execution API. It allows users to retrieve data by performing SQL requests using the Databricks API. The server is particularly effective when used in Agent mode, enabling it to handle multiple requests for complex tasks. Its functionality is further enhanced when integrated with Unity Catalog Metadata, providing a comprehensive solution for managing and querying data within Databricks. The server supports a range of operations, including listing schemas, tables, and views, as well as describing table schemas and retrieving SQL definitions of views. It is built to handle long-running queries efficiently by polling the Databricks API until completion or timeout.
Features
- Execute SQL queries on Databricks
- List available schemas in a catalog
- List tables in a schema
- Describe table schemas
- List views in a catalog and schema
Tools
execute_sql_query
Execute SQL query and return results
list_schemas
List all available patterns in a specific directory
list_tables
List all tables in a specific schema
describe_table
Describe the structure of the table