Databricks MCP Server

🚀 Databricks MCP Server

A Model Context Protocol (MCP) server for interacting with Databricks.

🚀 Quick Start

To use the Databricks MCP Server, follow these steps:

1. Download and install the version suitable for your system.
2. Start the server.
3. Use the provided tools to interact with the Databricks workspace.

✨ Features

The Databricks MCP Server provides a Model Context Protocol (MCP) interface for interacting with the Databricks workspace. It offers the following features:

List Catalogs

List all available catalogs in the Databricks workspace.

• Tool Name: list_catalogs
• Parameters: None
• Returns: A JSON array of catalog objects

List Schemas

List all schemas in a specified Databricks catalog.

• Tool Name: list_schemas
• Parameters:
  • catalog (string, required): The name of the catalog containing the schemas
• Returns: A JSON array of schema objects

List Tables

List all tables in a specified Databricks schema, with optional filtering.

• Tool Name: list_tables
• Parameters:
  • catalog (string, required): The name of the catalog containing the schema
  • schema (string, required): The name of the schema to list tables from
  • filter_pattern (string, optional, default: ".*"): A regular expression pattern for filtering table names
• Returns: A JSON array of table objects

Execute SQL

Execute an SQL statement on the Databricks SQL warehouse and return the results.

• Tool Name: execute_sql
• Parameters:
  • statement (string, required): The SQL statement to execute
  • timeout_seconds (number, optional, default: 60): The timeout in seconds for statement execution
  • row_limit (number, optional): The maximum number of rows to return
• Returns: A JSON object of the execution results

Supported Platforms

• Linux (amd64)
• Windows (amd64)
• macOS (amd64)

📦 Installation

You can download the latest version suitable for your platform from the Releases page.

VS Code

Install the Databricks MCP Server extension in VS Code via the following link:

Alternatively, you can manually install the extension by running the following commands:

# For VS Code
code --add-mcp '{"name":"databricks","command":"npx","args":["databricks-mcp-server@latest"]}'
# For VS Code Insiders
code-insiders --add-mcp '{"name":"databricks","command":"npx","args":["databricks-mcp-server@latest"]}'

💻 Usage Examples

List Catalogs

# Example command
curl -X POST http://localhost:8080/mcp/list_catalogs

List Schemas

# Example command
curl -X POST http://localhost:8080/mcp/list_schemas?catalog=my_catalog

List Tables

# Example command
curl -X POST http://localhost:8080/mcp/list_tables?catalog=my_catalog&schema=my_schema

📚 Documentation

Important Notes

⚠️ Important Note

Ensure that the server runs in a secure environment. Configure appropriate firewall rules to restrict access.

With these tools, you can conveniently interact with the Databricks workspace and perform various operations.