Model Context Protocol (MCP) finally gives AI models a way to access the business data needed to make them really useful at work. CData MCP Servers have the depth and performance to make sure AI has access to all of the answers.
Try them now for free →
Use Claude to Talk to Your Databricks Data via CData Connect Cloud
Leverage CData Connect Cloud Remote MCP to enable Claude to securely answer questions and take actions on your Databricks data for you.
Claude is a family of advanced large language models (LLMs) built by Anthropic, an AI research company founded in 2021. These models power the Claude conversational assistant and developer tools.
CData Connect Cloud offers a dedicated cloud-to-cloud interface for connecting to Databricks data. The CData Connect Cloud Remote MCP Server enables secure communication between Claude and Databricks. This allows you to ask questions and take actions on your Databricks data using Claude, all without the need for data replication to a natively supported database. With its inherent optimized data processing capabilities, CData Connect Cloud efficiently channels all supported SQL operations, including filters and JOINs, directly to Databricks. This leverages server-side processing to swiftly deliver the requested Databricks data.
About Databricks Data Integration
Accessing and integrating live data from Databricks has never been easier with CData. Customers rely on CData connectivity to:
- Access all versions of Databricks from Runtime Versions 9.1 - 13.X to both the Pro and Classic Databricks SQL versions.
- Leave Databricks in their preferred environment thanks to compatibility with any hosting solution.
- Secure authenticate in a variety of ways, including personal access token, Azure Service Principal, and Azure AD.
- Upload data to Databricks using Databricks File System, Azure Blog Storage, and AWS S3 Storage.
While many customers are using CData's solutions to migrate data from different systems into their Databricks data lakehouse, several customers use our live connectivity solutions to federate connectivity between their databases and Databricks. These customers are using SQL Server Linked Servers or Polybase to get live access to Databricks from within their existing RDBMs.
Read more about common Databricks use-cases and how CData's solutions help solve data problems in our blog: What is Databricks Used For? 6 Use Cases.
Getting Started
Step 1: Configure Databricks Connectivity for Claude
Connectivity to Databricks from Claude is made possible through CData Connect Cloud Remote MCP. To interact with Databricks data from Claude, we start by creating and configuring a Databricks connection in CData Connect Cloud.
- Log into Connect Cloud, click Sources, and then click Add Connection
- Select "Databricks" from the Add Connection panel
- Enter the necessary authentication properties to connect to Databricks.
To connect to a Databricks cluster, set the properties as described below.
Note: The needed values can be found in your Databricks instance by navigating to Clusters, and selecting the desired cluster, and selecting the JDBC/ODBC tab under Advanced Options.
- Server: Set to the Server Hostname of your Databricks cluster.
- HTTPPath: Set to the HTTP Path of your Databricks cluster.
- Token: Set to your personal access token (this value can be obtained by navigating to the User Settings page of your Databricks instance and selecting the Access Tokens tab).
- Click Save & Test
Step 2: Connect Claude to CData Connect Cloud
Follow these steps to add a CData Connect Cloud connector in Claude:
- Sign in to Claude.ai or create a new account.
- Expand the left navigation menu.
- In the bottom-left corner, click your user name and select Settings from the menu. The Settings screen appears.
- In the Settings screen, click Connectors.
- In the top-right corner, set your button toggle to Organization connectors.
- Click Add custom connector at the bottom of the page.
- Enter a name for the connector (such as Connect Cloud MCP).
- In the Remote MCP server URL field, enter https://mcp.cloud.cdata.com/mcp.
- Click Add to save the connector. The Connect Cloud MCP connector appears under Connectors.
- Click Connect to the right of the connector and enter your CData Connect Cloud user name and password. You have now connected Claude to CData Connect Cloud.
- Click the three dots after Connected and select Tools and settings.
- Review the provided tools and enable or disable specific tools made available by the server. In addition, determine whether you want unsupervised access to the tools, or whether you want Claude to ask your permission.
- Click Done when finished with your settings.
Step 3: Explore Live Databricks Databricks data with Claude
- In the left navigation menu of Claude, click New chat.
- You can now start exploring your data with natural language prompts. Claude outlines the steps it uses to retrieve data from the source in CData Connect Cloud. Refer to CData's prompt library for prompt ideas.
NOTE: Claude's setup process is subject to change. Refer to Claude's documentation for the latest setup information.
Get CData Connect Cloud
To get live data access to 100+ SaaS, Big Data, and NoSQL sources directly from your cloud applications, try CData Connect Cloud today!
