How to Use the Databricks MCP in CrewAI

Q: Can different agents in my CrewAI team have different access to Databricks tools?

Yes. When you configure the MCPServerHTTP tool in CrewAI, you can use the toolfilter argument. This lets you create specialized agents, like one that can only listclusters and another that can only listjobs in Databricks.

Q: Can a CrewAI agent find out which Databricks user it is running as?

It can. The getme tool returns the identity of the current user associated with the Databricks connection token. You could have an agent use this to log its actions or verify its permissions before proceeding.

Deploy an autonomous CrewAI team to monitor your Databricks environment 24/7 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 CrewAI

Create your Vinkius account to connect Databricks to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble a Databricks Monitoring Crew

This server provides the focused tools your CrewAI agents need to work as a team. Create a "Cluster Monitor" agent that only has access to `list_clusters` and `get_cluster`. Assign another agent as "Job Supervisor" with `list_jobs` and `list_job_runs`. They work together, each focused on its task. A third agent, the "Reporting Analyst," can take their findings and summarize the health of the entire Databricks workspace. This division of labor is CrewAI's main strength, and this MCP server provides the specific tools each agent needs to do its job.

Autonomous Catalog Auditing

With the tools in this server, your agents can now keep an eye on your Unity Catalog. Set up a "Catalog Watcher" agent to periodically run `list_catalogs` and `list_schemas`. It can build a picture of your data assets over time. When it detects a new schema or a change, it can pass that information to another agent in the crew. For example, a "Documentation Agent" could then be tasked with updating your data dictionary. This is how you build autonomous data governance with an MCP connection.

Your CrewAI's Eyes on Databricks

These tools are the senses for your autonomous crew. Without them, your agents are blind to what's happening inside Databricks. They can't manage what they can't see. You can selectively expose tools to different agents using CrewAI's `tool_filter`. Give the `get_me` tool only to a trusted "Admin" agent, while public-facing agents can only list resources. It’s granular control for building safe, autonomous systems, and this MCP Server is the bridge.

Setup guide

Set up Databricks MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Databricks tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Databricks Analyst",
    goal="Access and analyze Databricks data via MCP.",
    backstory="Expert analyst with direct Databricks access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Databricks transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Databricks Analyst",
        goal="Access and analyze Databricks data via MCP.",
        backstory="Expert analyst with direct Databricks access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Databricks transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You'd create a CrewAI agent with a recurring task. This agent would use the `list_job_runs` tool from this server to check for new job statuses. If it finds a failure, it can delegate a task to another agent to send an alert.

Yes. When you configure the `MCPServerHTTP` tool in CrewAI, you can use the `tool_filter` argument. This lets you create specialized agents, like one that can only `list_clusters` and another that can only `list_jobs` in Databricks.

The fastest way is to pass the Vinkius URL directly into your Agent's `mcps` list, like `mcps=["https://..."]`. CrewAI will automatically fetch the tools and make them available to the agent.

It can. The `get_me` tool returns the identity of the current user associated with the Databricks connection token. You could have an agent use this to log its actions or verify its permissions before proceeding.

The connection is scoped and secure. This server only provides access to Databricks metadata—things like job definitions, cluster configurations, and catalog names. Your actual table data is never exposed or accessed. Vinkius secures the connection with an ephemeral token specific to your session.

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