How to Use the Databricks MCP in Mastra AI

Build resilient Databricks workflows with Mastra AI. Automate job monitoring, retries, and cluster management with this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Databricks MCP to Mastra AI

Create your Vinkius account to connect Databricks to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Databricks with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Databricks Job Monitoring

This server's tools let your agent do more than just check job status; they let it act. With Mastra AI's workflow engine, you can build an agent that runs `list_job_runs`, finds a failed job, and automatically triggers a notification or a new process. You define the conditional logic. For example: if a job from `list_jobs` fails, check the cluster status with `get_cluster`. If the cluster is down, page the on-call engineer. If not, retry the job. Mastra handles the state and retries for you.

Build Self-Healing Compute Logic

These tools help your agent build pipelines that don't fail when a cluster is resizing. Your Mastra agent can use `list_clusters` to check the state of your compute resources before submitting work. If a cluster isn't ready, Mastra's built-in exponential backoff can wait and check again. This makes your data operations much more robust. You can combine checks for `list_clusters` and `list_warehouses` to ensure all necessary compute is online before a critical workflow begins. It's proactive infrastructure management, powered by an MCP Server.

A Resilient MCP Server for Databricks

This MCP Server gives your Mastra agent the basic senses it needs to understand your Databricks environment. It can list resources with tools like `list_catalogs` and `list_schemas` to get a lay of the land before it acts. Combine this awareness with Mastra's `requireToolApproval` for a human-in-the-loop workflow. The agent can propose a plan—like restarting a job—based on data from `list_job_runs`, then wait for a human to approve it in Slack before executing.

Setup guide

Set up Databricks MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Databricks tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "databricks-mcp-client",
  servers: {
    "databricks-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Databricks Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Databricks tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Databricks transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Databricks. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Databricks now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Databricks MCP in Mastra AI

Mastra has automatic retries with exponential backoff built in. If a call to `list_clusters` fails due to a network blip, Mastra will try again automatically, making your automations more reliable.

Yes, that's Mastra's specialty. You can define a workflow where an agent first checks job status with `list_job_runs`, then uses conditional logic to decide whether to check cluster health with `get_cluster` or notify a user.

After installing the Mastra MCP package, you instantiate the `MCPClient` with your Vinkius server URL. Then you call `mcpClient.listTools()` and spread the result into your agent's toolset. Mastra handles the rest.

A classic example is building a self-managing ETL pipeline. Use Mastra AI to orchestrate a process that waits for a Databricks cluster to be available (`list_clusters`), runs a job, monitors its status (`list_job_runs`), and sends a Slack message on success or failure.

Absolutely. The server only deals with operational metadata: job names, cluster states, schema listings. It has no access to the actual data stored in your lakehouse. Your connection is protected by a unique Vinkius token, and all operations happen over a secure channel.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript