UBOS Asset Marketplace: CData MCP Server for Databricks - Empowering AI with Seamless Data Connectivity

In today’s data-driven world, the ability to connect Large Language Models (LLMs) like Claude to live data sources is paramount for informed decision-making and advanced AI applications. The UBOS Asset Marketplace features the CData Model Context Protocol (MCP) Server for Databricks, a powerful tool designed to bridge the gap between your Databricks data and AI models. This read-only MCP Server leverages CData JDBC Drivers to expose Databricks data as relational SQL models, enabling LLMs to query live information using natural language, eliminating the need for complex SQL queries.

Understanding the Model Context Protocol (MCP)

Before diving into the specifics of the CData MCP Server, it’s crucial to understand what MCP is and why it’s essential. MCP is an open protocol that standardizes how applications provide context to LLMs. Think of it as a universal language that allows AI models to understand and interact with external data sources and tools. An MCP server acts as the intermediary, translating requests from the LLM into a format that the data source can understand and then relaying the response back to the LLM.

Why the CData MCP Server for Databricks Matters

The CData MCP Server for Databricks offers a streamlined solution for integrating your Databricks data with AI models. Here’s why it’s a game-changer:

• Natural Language Data Access: LLMs can query Databricks data using natural language questions, making data access more intuitive and accessible to a wider range of users.
• No SQL Required: Eliminates the need for users to write complex SQL queries, simplifying the data retrieval process.
• Live Data Integration: LLMs can retrieve live information from Databricks, ensuring that decisions are based on the most up-to-date data.
• Simplified Setup: The server wraps the CData JDBC Driver, making Databricks data available through a simple MCP interface.

Key Features and Benefits

The CData MCP Server for Databricks boasts a range of features that make it an invaluable asset for any organization leveraging Databricks and AI. Let’s explore some of the key highlights:

• Read-Only Access: The server provides read-only access to Databricks data, ensuring data integrity and security.
• CData JDBC Driver Integration: Leverages the power and reliability of CData JDBC Drivers for seamless connectivity to Databricks.
• SQL Modeling: Exposes Databricks data as relational SQL models, making it easier for LLMs to understand and process the data.
• Easy Setup and Configuration: The server is designed for easy setup and configuration, allowing you to quickly connect your Databricks data to AI models.
• JSON-RPC Support: Supports JSON-RPC 2.0 specification for scripting requests to the MCP Server, enabling advanced automation and integration.
• Comprehensive Documentation: Provides detailed documentation and examples to help you get started and troubleshoot any issues.

Use Cases: Unleashing the Potential of AI with Databricks Data

The CData MCP Server for Databricks unlocks a plethora of use cases across various industries and applications. Here are a few examples:

• Business Intelligence: Use LLMs to analyze Databricks data and generate insights into business performance, trends, and opportunities. For instance, an AI agent could answer: “What is the correlation between my closed won opportunities and the account industry?”
• Customer Support: Integrate Databricks data with customer support platforms to provide AI-powered assistance to customers. An example question for an AI agent: “How many open tickets do I have in the SUPPORT project?”
• Sales and Marketing: Leverage AI to personalize sales and marketing efforts based on Databricks data. An AI agent can quickly provide you with this: “Can you tell me what calendar events I have today?”
• Data Analysis and Reporting: Streamline data analysis and reporting by using LLMs to query Databricks data and generate reports in natural language.
• AI-Powered Applications: Build custom AI-powered applications that leverage Databricks data to provide intelligent services and solutions.

Getting Started with the CData MCP Server for Databricks

To get started with the CData MCP Server for Databricks, follow these steps:

1. Clone the Repository: Clone the repository from GitHub:

   bash git clone https://github.com/cdatasoftware/databricks-mcp-server-by-cdata.git cd databricks-mcp-server-by-cdata

2. Build the Server: Build the server using Maven:

   bash mvn clean install

   This will create the JAR file: CDataMCP-jar-with-dependencies.jar

3. Download and Install the CData JDBC Driver for Databricks: Download and install the CData JDBC Driver for Databricks from https://www.cdata.com/drivers/databricks/download/jdbc.

4. License the CData JDBC Driver: License the driver by navigating to the lib folder in the installation directory and running the command:

   bash java -jar cdata.jdbc.databricks.jar --license

   Enter your name, email, and “TRIAL” (or your license key).

5. Configure your connection to Databricks: Run the command java -jar cdata.jdbc.databricks.jar to open the Connection String utility. Configure the connection string and click “Test Connection”. Copy the connection string for use later.

6. Create a .prp file for your JDBC connection: Create a .prp file (e.g., databricks.prp) with the following properties:

   env Prefix=databricks ServerName=CDataDatabricks ServerVersion=1.0 DriverPath=PATHTOcdata.jdbc.databricks.jar DriverClass=cdata.jdbc.databricks.DatabricksDriver JdbcUrl=jdbc:databricks:InitiateOAuth=GETANDREFRESH;… Tables=

7. Configure Claude Desktop (or your AI client): Create a config file (claude_desktop_config.json) to add the new MCP server. Add an entry to the mcpServers section with the following format:

   { “mcpServers”: { “{classname_dash}”: { “command”: “PATHTOjava.exe”, “args”: [ “-jar”, “PATHTOCDataMCP-jar-with-dependencies.jar”, “PATHTOdatabricks.prp” ] } } }

8. Run or Refresh your Client: Run or refresh your AI client (e.g., Claude Desktop). You may need to fully exit and re-open the client for the MCP Servers to appear.

Diving Deeper: Tools and JSON-RPC Examples

The CData MCP Server for Databricks provides several tools that can be used to interact with Databricks data. These tools can be accessed through JSON-RPC requests. Here’s a breakdown of the available tools and examples:

• {servername}_get_tables: Retrieves a list of tables available in the data source.

  { “jsonrpc”: “2.0”, “id”: 1, “method”: “tools/call”, “params”: { “name”: “databricks_get_tables”, “arguments”: {} } }

• {servername}_get_columns: Retrieves a list of columns for a table.

  { “jsonrpc”: “2.0”, “id”: 2, “method”: “tools/call”, “params”: { “name”: “databricks_get_columns”, “arguments”: { “table”: “Account” } } }

• {servername}_run_query: Executes a SQL SELECT query.

  { “jsonrpc”: “2.0”, “id”: 3, “method”: “tools/call”, “params”: { “name”: “databricks_run_query”, “arguments”: { “sql”: “SELECT * FROM [Account] WHERE [IsDeleted] = true” } } }

Troubleshooting Tips

• If you cannot see your CData MCP Server in your AI client, ensure you have fully quit and restarted the client.
• If the AI client is unable to retrieve data, verify that you have configured your connection properly using the Connection String builder.
• For issues connecting to your data source, contact the CData Support Team.
• For issues using the MCP server, join the CData Community.

The UBOS Advantage: Powering AI Agents with Seamless Data Access

The CData MCP Server for Databricks seamlessly integrates with the UBOS platform, a full-stack AI Agent Development Platform that empowers businesses to orchestrate AI Agents, connect them with enterprise data, build custom AI Agents with their own LLM models, and create sophisticated Multi-Agent Systems.

By integrating the CData MCP Server for Databricks with UBOS, you can:

• Centralize Data Access: Provide a single point of access to all your Databricks data for your AI Agents.
• Enhance AI Agent Capabilities: Enable your AI Agents to make more informed decisions by providing them with access to live, up-to-date data.
• Automate Data-Driven Tasks: Automate tasks that require access to Databricks data, such as generating reports, analyzing trends, and personalizing customer experiences.
• Build Custom AI Solutions: Create custom AI solutions that leverage Databricks data to solve specific business problems.

In conclusion, the CData MCP Server for Databricks, available on the UBOS Asset Marketplace, is a powerful tool that enables seamless integration between your Databricks data and AI models. By leveraging this server, you can unlock the full potential of AI and drive data-driven innovation across your organization. This integration empowers your AI agents to deliver actionable insights, automate complex tasks, and ultimately, contribute to a more efficient and intelligent business operation.