DatabricksMCP

Purvanshsingh/DatabricksMCP

★ 0 stars Python AI/LLM Updated today

DatabricksMCP is an open-source Model Context Protocol (MCP) server for Databricks. It lets AI agents securely query Databricks SQL, explore Unity Catalog, run Jobs/Notebooks, and use Vector Search. Designed for governed, auditable workflows, it makes Databricks a first-class MCP integration.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "databricksmcp": {
      "command": "uvx",
      "args": [
        "databricksmcp"
      ]
    }
  }
}

Or install with pip: pip install databricksmcp

README Excerpt

<img src="assets/databricksmcp-wordmark.svg" alt="DatabricksMCP" width="820"> The open, policy-first MCP control plane for Databricks. Governed access to data, SQL, workflows, compute, workspace assets, governance, ML/AI, and cost through one extensible Model Context Protocol server.

Tools (12)

DATABRICKS_MCP_ACCESS_MODEDATABRICKS_MCP_APPROVAL_TTL_SECONDSDATABRICKS_MCP_DEFAULT_PAGE_SIZEDATABRICKS_MCP_HOSTDATABRICKS_MCP_LOG_LEVELDATABRICKS_MCP_PORTDATABRICKS_MCP_SQL_BYTE_LIMITDATABRICKS_MCP_SQL_MAX_ROWSDATABRICKS_MCP_SQL_WAIT_SECONDSDATABRICKS_MCP_SQL_WAREHOUSESDATABRICKS_MCP_TRANSPORTDATABRICKS_MCP_WRITE_TOOLS_ALLOW

DatabricksMCP

Quick Install

README Excerpt

Tools (12)

Related AI/LLM Servers