Skip to main content The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench Explore Tool Discovery
StackOne
Connectors
Pricing
Login
Book Demo Start Free
Connect

Connect to everything your agents need, without writing the infrastructure to get there.

Secure

Enterprise-grade controls to ensure your agent always meets security & compliance standards.

Optimize

Maximise agent efficiency – faster responses, increased accuracy, fewer tokens used.

Explore more use-cases
Closing the Loop: A Self-Evolving Defense
New
StackOne
Connectors
Connect

Connect to everything your agents need, without writing the infrastructure to get there.

Secure

Enterprise-grade controls to ensure your agent always meets security & compliance standards.

Optimize

Maximise agent efficiency – faster responses, increased accuracy, fewer tokens used.

Use-Cases
Pricing
Book Demo Start Free
Live 36 Actions

Databricks Workspace MCP Server
for AI Agents

Connect your AI agent to StackOne's Databricks Workspace MCP server and give it 36 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →
Databricks Workspace logo
Databricks Workspace MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

36 Agent Actions

Create, read, update, and delete across Databricks Workspace — and extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Databricks Workspace MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Databricks Workspace tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Databricks Workspace call.

Tools Discovery →

What is the Databricks Workspace MCP Server?

A Databricks Workspace MCP server lets AI agents read and write Databricks Workspace data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Databricks Workspace MCP server ships with 36 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Databricks Workspace MCP Tools

Every action from Databricks Workspace's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Clusters

  • Create Cluster

    Create a new Databricks compute cluster with the supplied configuration

  • List Clusters

    List all pinned, active, and recently terminated clusters in the workspace

  • Get Cluster

    Retrieve the configuration and state of a specific cluster by ID

Jobs

  • Create Job

    Create a new job in the workspace

  • List Jobs

    List all jobs in the workspace

  • Get Job

    Get details of a specific job

  • Update Job

    Partially update a job's settings

  • Delete Job

    Delete a job from the workspace

Job Runs

  • List Job Runs

    List runs for a specific job or all runs in the workspace

  • Get Job Run

    Get details of a specific job run

SQL Warehouses

  • Create SQL Warehouse

    Create a new SQL warehouse

  • List SQL Warehouses

    List all SQL warehouses in the workspace

  • Get SQL Warehouse

    Get details of a specific SQL warehouse

  • Delete SQL Warehouse

    Delete a SQL warehouse

Workspace Objects

  • Import Workspace Object

    Import a notebook or file into the workspace

  • List Workspace Objects

    List objects in a workspace directory

  • Export Workspace Object

    Export a notebook or file from the workspace

  • Delete Workspace Object

    Delete a workspace object

Other (18)

  • Create Workspace Directory

    Create a directory in the workspace

  • List Spark Versions

    List the Spark versions available for use when creating a new cluster

  • List Node Types

    List the supported node types available for cluster worker and driver nodes

  • Get Job Run Output

    Get the output of a completed job run task

  • Get SQL Statement

    Get the status and results of a SQL statement execution

  • Get Workspace Object Status

    Get metadata for a workspace object

  • Edit Cluster

    Update the configuration of an existing cluster to match the supplied attributes

  • Start Cluster

    Start a terminated Spark cluster using its existing configuration

  • Restart Cluster

    Restart a Spark cluster that is currently running

  • Terminate Cluster

    Terminate a running cluster while preserving its configuration

  • Permanently Delete Cluster

    Permanently delete a cluster, removing its configuration entirely

  • Run Job

    Trigger a job run immediately

  • Cancel Job Run

    Cancel an active job run

  • Execute SQL Statement

    Execute a SQL statement on a warehouse

  • Cancel SQL Statement

    Cancel a running SQL statement execution

  • Edit SQL Warehouse

    Update configuration of an existing SQL warehouse

  • Start SQL Warehouse

    Start a stopped SQL warehouse

  • Stop SQL Warehouse

    Stop a running SQL warehouse

Set Up Your Databricks Workspace MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Databricks Workspace in under 10 lines of code.

MCP Clients

Claude Desktop setup guide
Claude Code setup guide
Cursor setup guide
Goose setup guide

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

Platform Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.

11 min

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.

12 min

MCP vs A2A: Architecture, Security, and When to Use Each

MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.

12 min

MCP vs API: What 200+ Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.

14 min read

Databricks Workspace MCP Server FAQ

Does StackOne have a Databricks Workspace MCP server?
Yes. StackOne offers a hosted Databricks Workspace MCP server with 36 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Databricks Workspace MCP server vs direct API integration — what's the difference?
A Databricks Workspace MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Databricks Workspace. A Databricks Workspace MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Databricks Workspace at runtime. StackOne provides both.
How does Databricks Workspace authentication work for AI agents?
Databricks Workspace authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Databricks Workspace account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Databricks Workspace MCP tools vulnerable to prompt injection?
Yes — Databricks Workspace MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Databricks Workspace agent and how do I avoid it?
Context bloat happens when Databricks Workspace tool schemas and API responses eat your Databricks Workspace agent's memory, preventing it from reasoning effectively. A single Databricks Workspace query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Databricks Workspace agent can access?
Yes — you can limit which actions your Databricks Workspace agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Databricks Workspace MCP server?
Yes — you can create custom agent actions for your Databricks Workspace MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Databricks Workspace's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Databricks Workspace MCP server?
Skip a Databricks Workspace MCP server if your integration is purely software-to-software — direct Databricks Workspace API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Databricks Workspace actions at runtime.
What AI frameworks and AI clients does the StackOne Databricks Workspace MCP server support?
The StackOne Databricks Workspace MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.

Start Free Book Demo