How do I install the mcp server?

Use a recorded configuration for your client, replace example credential values and paths, and verify the documented runtime. Restart or reconnect the client, then inspect the available tools.

SSyncDev

Start a project

MCP Server — databrickslabs/mcp

The set of servers and tools in this repo is fluid and will evolve over time. We welcome contributions to this repo - please first read the

Local serverstdioPython

What is the MCP Server?

The set of servers and tools in this repo is fluid and will evolve over time. We welcome contributions to this repo - please first read the [contributor

What the server does

An experimental collection of MCP servers to help AI agents fetch enterprise data from Databricks, automate common developer actions on Databricks, etc:

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

How to install the MCP Server

{
  "mcpServers": {
    "databricks_unity_catalog": {
      "command": "/path/to/uv/executable/uv",
      "args": [
        "--directory",
        "/path/to/this/repo",
        "run",
        "unitycatalog-mcp",
        "-s",
        "your_catalog.your_schema",
        "-g",
        "genie_space_id_1,genie_space_id_2"
      ]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

“Use MCP to Overview.”

Frequently asked questions

The set of servers and tools in this repo is fluid and will evolve over time. We welcome contributions to this repo - please first read the [contributor Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.