Databricks MCP Server
A comprehensive server for Databricks, built on the official .
Potencialize seu agente
O comando do próprio publicador. Não é um endpoint do PlugMCP.
Host a copy with our keys and logs.
uvx databricks-sdk-mcp==0.1.0O Claude Code não tem link de instalação para um comando local. Copie o comando abaixo e execute-o em um terminal.
DATABRICKS_HOST=<value> DATABRICKS_TOKEN=<secret> DATABRICKS_MCP_TOOLS_INCLUDE=<value> claude mcp add io.github.pramodbhatofficial-databricks-sdk-mcp -- uvx databricks-sdk-mcp==0.1.0Execute em um terminal.
{ "mcpServers": { "io.github.pramodbhatofficial-databricks-sdk-mcp": { "command": "uvx", "args": [ "databricks-sdk-mcp==0.1.0" ], "env": { "DATABRICKS_HOST": "<value>", "DATABRICKS_TOKEN": "<secret>", "DATABRICKS_MCP_TOOLS_INCLUDE": "<value>" } } }}claude_desktop_config.json
URL remota ou um comando na sua máquina? Como as duas instalações diferem
Rodar no PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
AbrirProvides 263 tools and 8 prompt templates across 28 service domains, giving AI assistants full access to the Databricks platform.
databricks-sdk for type safety and automatic API freshnesspip install databricks-sdk-mcp
Or run with Docker:
docker run -i -e DATABRICKS_HOST=... -e DATABRICKS_TOKEN=... databricks-mcp
Or install from source:
git clone https://github.com/pramodbhatofficial/databricks-mcp-server.git
cd databricks-mcp-server
pip install -e ".[dev]"
Authentication is handled by the Databricks SDK. Set one of:
Personal Access Token (simplest):
export DATABRICKS_HOST=https://your-workspace.databricks.com
export DATABRICKS_TOKEN=dapi...
OAuth (M2M -- service principal):
export DATABRICKS_HOST=https://your-workspace.databricks.com
export DATABRICKS_CLIENT_ID=...
export DATABRICKS_CLIENT_SECRET=...
OAuth (U2M -- interactive browser login):
Authenticate as yourself with short-lived, auto-refreshing OAuth tokens. Log in once
with the Databricks CLI, which
caches the token under a named profile in ~/.databrickscfg:
databricks auth login --host https://your-workspace.databricks.com --profile my-profile
Then point the server at that profile instead of setting a token:
export DATABRICKS_CONFIG_PROFILE=my-profile
Note: If
DATABRICKS_TOKENis set, the SDK uses it in preference to the profile. LeaveDATABRICKS_TOKEN/DATABRICKS_HOSTunset when authenticating via a profile.
Other methods: Azure AD, Azure Managed Identity -- all auto-detected by the SDK.
databricks-mcp
This starts the MCP server using stdio transport.
Add to ~/.claude/settings.json or your project's .claude/settings.json:
{
"mcpServers": {
"databricks": {
"command": "databricks-mcp",
"env": {
"DATABRICKS_HOST": "https://your-workspace.databricks.com",
"DATABRICKS_TOKEN": "dapi..."
}
}
}
}
To use OAuth U2M instead of a token, reference a logged-in profile (see
Authentication) and omit DATABRICKS_HOST/DATABRICKS_TOKEN:
{
"mcpServers": {
"databricks": {
"command": "databricks-mcp",
"env": {
"DATABRICKS_CONFIG_PROFILE": "my-profile"
}
}
}
}
Then restart Claude Code. Verify with /mcp to see the registered tools.
Add to your Claude Desktop config file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": {
"databricks": {
"command": "databricks-mcp",
"env": {
"DATABRICKS_HOST": "https://your-workspace.databricks.com",
"DATABRICKS_TOKEN": "dapi..."
}
}
}
}
Restart Claude Desktop. The Databricks tools will appear in the tool picker.
Add to .cursor/mcp.json in your project root (or ~/.cursor/mcp.json for global):
{
"mcpServers": {
"databricks": {
"command": "databricks-mcp",
"env": {
"DATABRICKS_HOST": "https://your-workspace.databricks.com",
"DATABRICKS_TOKEN": "dapi..."
}
}
}
}
Open Cursor Settings > MCP to verify the server is connected.
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"databricks": {
"command": "databricks-mcp",
"env": {
"DATABRICKS_HOST": "https://your-workspace.databricks.com",
"DATABRICKS_TOKEN": "dapi..."
}
}
}
}
Add to .vscode/mcp.json in your project:
{
"servers": {
"databricks": {
"command": "databricks-mcp",
"env": {
"DATABRICKS_HOST": "https://your-workspace.databricks.com",
"DATABRICKS_TOKEN": "dapi..."
}
}
}
}
Add to Zed's settings (~/.config/zed/settings.json):
{
"context_servers": {
"databricks": {
"command": {
"path": "databricks-mcp",
"env": {
"DATABRICKS_HOST": "https://your-workspace.databricks.com",
"DATABRICKS_TOKEN": "dapi..."
}
}
}
}
}
The server uses stdio transport. Connect from any MCP-compatible client:
# Set auth env vars
export DATABRICKS_HOST=https://your-workspace.databricks.com
export DATABRICKS_TOKEN=dapi...
# Start the server (communicates via stdin/stdout)
databricks-mcp
If your MCP client struggles with many tools, use selective loading to reduce the tool count:
{
"mcpServers": {
"databricks": {
"command": "databricks-mcp",
"env": {
"DATABRICKS_HOST": "https://your-workspace.databricks.com",
"DATABRICKS_TOKEN": "dapi...",
"DATABRICKS_MCP_TOOLS_INCLUDE": "unity_catalog,sql,compute,jobs"
}
}
}
}
With 263 tools, it's recommended to load only the modules you need. This improves agent performance and tool selection accuracy.
Pick a preset that matches your role:
Example using a preset in Claude Code:
{
"mcpServers": {
"databricks": {
"command": "databricks-mcp",
"env": {
"DATABRICKS_HOST": "https://your-workspace.databricks.com",
"DATABRICKS_TOKEN": "dapi...",
"DATABRICKS_MCP_TOOLS_INCLUDE": "unity_catalog,sql,compute,jobs,pipelines,files,quality_monitors"
}
}
}
}
# Only include specific modules
export DATABRICKS_MCP_TOOLS_INCLUDE=unity_catalog,sql,serving
# Exclude specific modules (cannot combine with INCLUDE)
export DATABRICKS_MCP_TOOLS_EXCLUDE=iam,sharing,experiments
If INCLUDE is set, only those modules load. If EXCLUDE is set, everything except those modules loads. INCLUDE takes precedence if both are set.
The server includes built-in tool discovery to help AI agents find the right tools:
Agents can read databricks://tools/guide at connection time to understand what's available.
The databricks_tool_guide tool helps agents find the right tools during a conversation:
# Find tools for a specific task
databricks_tool_guide(task="run a SQL query")
databricks_tool_guide(task="deploy an ML model")
databricks_tool_guide(task="create a user")
# Get role-based recommendations
databricks_tool_guide(role="data_engineer")
databricks_tool_guide(role="ml_engineer")
This returns matching modules with descriptions and usage hints, so the agent knows exactly which databricks_* tools to call.
The server includes 8 prompt templates that guide AI agents through multi-step Databricks workflows:
Prompts appear automatically in MCP clients that support them (e.g., Claude Desktop's prompt picker).
Run the MCP server in a container:
# Build
docker build -t databricks-mcp .
# Run with stdio
docker run -i \
-e DATABRICKS_HOST=https://your-workspace.databricks.com \
-e DATABRICKS_TOKEN=dapi... \
databricks-mcp
# Run with SSE transport
docker run -p 8080:8080 \
-e DATABRICKS_HOST=https://your-workspace.databricks.com \
-e DATABRICKS_TOKEN=dapi... \
databricks-mcp --transport sse --port 8080
# Run with selective modules
docker run -i \
-e DATABRICKS_HOST=https://your-workspace.databricks.com \
-e DATABRICKS_TOKEN=dapi... \
-e DATABRICKS_MCP_TOOLS_INCLUDE=sql,unity_catalog \
databricks-mcp
The server supports SSE transport for remote connections:
# Start as SSE server
databricks-mcp --transport sse --port 8080
# Custom host/port
databricks-mcp --transport sse --host 127.0.0.1 --port 3000
Connect from any MCP client that supports SSE:
{
"mcpServers": {
"databricks": {
"url": "http://localhost:8080/sse"
}
}
}
# Install with dev dependencies
pip install -e ".[dev]"
# Lint
ruff check databricks_mcp/
# Test
pytest tests/ -v
Pramod Bhat
Apache 2.0 -- see LICENSE.
263 tools for Databricks: Unity Catalog, SQL, Compute, Jobs, Serving, and more.
{ "mcpServers": { "io.github.pramodbhatofficial-databricks-sdk-mcp": { "command": "uvx", "args": [ "databricks-sdk-mcp==0.1.0" ], "env": { "DATABRICKS_HOST": "<value>", "DATABRICKS_TOKEN": "<secret>", "DATABRICKS_MCP_TOOLS_INCLUDE": "<value>" } } }}Ferramentas
Ainda não há lista de ferramentas. Servidores remotos recebem uma após a primeira verificação de saúde.
Perguntas frequentes
Copie nesta página a configuração stdio para Cursor, Claude Desktop, Claude Code ou VS Code. Ela usa a instalação do publicador, não um proxy do PlugMCP.
O publicador lista estas variáveis de ambiente: DATABRICKS_HOST, DATABRICKS_TOKEN, DATABRICKS_MCP_TOOLS_INCLUDE.
Databricks MCP Server roda localmente via stdio.
Última verificação: 2026-11-10. 263 tools for Databricks: Unity Catalog, SQL, Compute, Jobs, Serving, and more.