Databricks MCP server

This is a small helper that connects your AI assistant to Databricks, the place where your company keeps data and runs jobs. Once it is set up, you can ask your AI in plain English to run a query or check on a job, and it will do it for you. It is handy if you already use Databricks at work but do not want to click around the website every time.

What this MCP server does

You type a request in your AI chat, like asking for a count of rows in a table. Your AI sends that request to this helper program running on your computer. The helper logs into Databricks using your personal access token and runs the SQL query or looks up the job you asked about. Databricks sends the result back, and the helper hands it to your AI. Your AI then shows you the answer in the chat, as a table, a list, or a short summary.

Click to zoom

What you can do with it

• Run SQL queries on your Databricks SQL warehouse
• List all the jobs in your Databricks workspace
• Check the status of a specific job by its ID
• Get detailed information about a job, like its settings and schedule
• Ask questions about your data in plain English and get results back
• Look up which tables exist in a database

Try asking your AI

• “Show me all tables in the database”
• “Run a query to count records in the customer table”
• “List all my Databricks jobs”
• “Check the status of job 123”

What it gives back to you

You get answers right in your AI chat. For a query, that is usually a small table or a number, like the count of rows. For jobs, you get a list of job names and IDs, or the status of one job, such as running, succeeded, or failed. For job details, you get a longer description with things like the schedule and settings.

Before you start

Who it's for

Office workers and analysts who already use Databricks at work and want to ask questions or check jobs without clicking through the Databricks website.