How to Use the Databricks MCP in LangChain

Q: How do I use the Databricks tools with LangChain to check job status?

Your agent can call listjobs to find the job, then pass its ID to listjobruns. This gives you a complete history that your LangChain agent can parse to check for recent failures.

Q: Can my LangChain agent list all Databricks SQL warehouses?

Yes. Just give the agent access to the listwarehouses tool. It will return a list of all SQL warehouses and their current status, which you can use as part of a larger chain.

Build LangChain agents that run complex sequences of commands against your Databricks lakehouse.

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 LangChain

Create your Vinkius account to connect Databricks to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Together Databricks Checks

Your LangChain agent can now run a sequence of checks against Databricks. It can start by calling `list_clusters` to find the right compute, then use `get_cluster` to check its state, and finish by calling `list_job_runs` to see what's currently running. The agent decides the order based on the goal you give it. This isn't just about getting data; it's about building automated logic. You can create a pre-deployment check that confirms a target cluster is active and idle before your CI/CD pipeline proceeds. With LangSmith, you can trace the entire chain of tool calls, seeing exactly what the agent did with the Databricks tools.

Build Agents to Audit Unity Catalog

Give your agent the tools to explore your data estate. It can start with `list_catalogs` to get a top-level view, then loop through the results and call `list_schemas` for each one. This creates a dynamic map of your Unity Catalog. This is how you build an automated governance bot. Set up a recurring chain where an agent traverses your catalogs, checks for schemas that don't meet your naming conventions, and flags them. The agent combines reasoning with direct access to your Databricks metadata.

Use Your LangChain Agent to Manage Jobs

An agent can monitor your entire job infrastructure. It uses `list_jobs` to get a complete inventory, then digs into specific runs with `list_job_runs` to check for failures or long execution times. It can also keep an eye on your SQL compute by calling `list_warehouses`. This Databricks MCP Server lets you hand off operational tasks. Instead of manually checking logs, you tell your agent a high-level goal like, "Let me know if the main ETL job has failed in the last 24 hours." The agent figures out the right sequence of tool calls to get you the answer.

Setup guide

Set up Databricks MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Databricks tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "databricks-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Databricks transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Your agent can call `list_jobs` to find the job, then pass its ID to `list_job_runs`. This gives you a complete history that your LangChain agent can parse to check for recent failures.

Yes. Just give the agent access to the `list_warehouses` tool. It will return a list of all SQL warehouses and their current status, which you can use as part of a larger chain.

It's a few lines of code. After installing the adapter, you instantiate the `MultiServerMCPClient` with your Vinkius endpoint URL. Then you call `get_tools()` and pass the resulting list to your agent.

The tool call will raise an exception in your chain. You can configure your agent's error handling to retry, try a different tool, or report the failure back to you.

The server only accesses the data you ask for, like cluster names, job IDs, and schema names. Each request runs in an ephemeral, single-use sandbox on Vinkius. Your connection is secured by a unique endpoint token, not your raw Databricks credentials.

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