Databricks By Cdata MCP Server

CData JDBC Driver connects to Databricks by exposing them as relational SQL models.

Remote serverstreamable-http

What is the Databricks By Cdata MCP server?

Databricks By Cdata MCP server exists for a simple reason — assistants are far more useful when they can act on Databricks By Cdata directly instead of describing what you should do. CData JDBC Driver connects to Databricks by exposing them as relational SQL models.

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

What the assistant can call

Once Databricks By Cdata is connected, these are the calls the assistant has available:

  • databricks_get_tables — The databricks_get_tables tool exposed by this server
  • databricks_get_columns — The databricks_get_columns tool exposed by this server
  • databricks_run_query — The databricks_run_query tool exposed by this server

Before you rely on it

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the databricks by cdata mcp server does with a few real requests.

Choosing this one

Among the database access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Databricks By Cdata's toolset — databricks_get_tables, databricks_get_columns, databricks_run_query — is a fair guide to whether it matches your workflow. It is maintained by CDataSoftware; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
databricks_get_tablesThe databricks_get_tables tool exposed by this server.
databricks_get_columnsThe databricks_get_columns tool exposed by this server.
databricks_run_queryThe databricks_run_query tool exposed by this server.

How to install the Databricks By Cdata MCP server

**Linux/Mac**
      ```json
      {
        "mcpServers": {
          "{classname_dash}": {
            "command": "/PATH/TO/java",
            "args": [
              "-jar",
              "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
              "/PATH/TO/databricks.prp"
            ]
          },
          ...
        }
      }

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Databricks By Cdata to databricks get tables.
  • Use Databricks By Cdata to databricks get columns.
  • Use Databricks By Cdata to databricks run query.

Frequently asked questions

It connects Databricks By Cdata to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (databricks_get_tables, databricks_get_columns, databricks_run_query) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Databricks By Cdata directly.