Unlock Oracle Financials Cloud Data for AI with UBOS and CData MCP Server

In today’s data-driven world, leveraging the power of Large Language Models (LLMs) like Claude for business insights is becoming increasingly crucial. However, accessing and integrating data from various sources, such as Oracle Financials Cloud, can be a complex challenge. That’s where the UBOS AI Agent Development Platform, in conjunction with CData’s Model Context Protocol (MCP) Server, provides a seamless and efficient solution.

This document outlines how you can use the CData MCP Server for Oracle Financials Cloud to connect your financial data to Claude Desktop, enabling you to ask natural language questions and retrieve live information without the need for complex SQL queries. We’ll also explore how UBOS enhances this integration by providing a full-stack AI Agent development platform, allowing you to build and orchestrate custom AI Agents that leverage this data for various business use cases.

The Challenge: Bridging the Gap Between Data and AI

LLMs like Claude are powerful tools for extracting insights and automating tasks. However, they need access to relevant data to be truly effective. Traditionally, accessing data from systems like Oracle Financials Cloud required technical expertise in SQL and database management.

The MCP Server solves this problem by providing a standardized way for LLMs to interact with external data sources. It acts as a bridge, translating natural language queries into SQL queries and returning the results in a format that the LLM can understand.

CData MCP Server for Oracle Financials Cloud: A Read-Only Solution

The CData MCP Server for Oracle Financials Cloud is a read-only server that allows you to connect to your Oracle Financials Cloud data from Claude Desktop. It leverages the CData JDBC Driver for Oracle Financials Cloud, which exposes the data as relational SQL models.

Key Features:

• Natural Language Querying: Ask questions in plain English and get answers based on your Oracle Financials Cloud data.
• Live Data Access: Retrieve real-time information from your financial system.
• Simplified Setup: Easy-to-follow instructions for setting up the server and connecting it to Claude Desktop.
• SQL Translation: The server automatically translates natural language queries into SQL queries, so you don’t need to write any code.
• JDBC Driver Integration: Built on the robust and reliable CData JDBC Driver for Oracle Financials Cloud.

Use Cases:

• Financial Reporting: Generate reports on key financial metrics by simply asking questions like, “What is the total revenue for the last quarter?”
• Data Analysis: Analyze financial trends and patterns by asking questions like, “What is the correlation between sales and marketing spend?”
• Decision Making: Make informed decisions based on real-time financial data.
• Improved Efficiency: Automate tasks that previously required manual data extraction and analysis.

Setting up the CData MCP Server (Read-Only)

Here’s a step-by-step guide to setting up the read-only CData MCP Server for Oracle Financials Cloud:

1. Clone the Repository:

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

2. Build the Server:

   bash mvn clean install

   This creates the JAR file: CDataMCP-jar-with-dependencies.jar

3. Download and Install the CData JDBC Driver for Oracle Financials Cloud: https://www.cdata.com/drivers/oracleerp/download/jdbc

4. License the CData JDBC Driver:

   • Navigate to the lib folder in the installation directory (e.g., C:Program FilesCDataCData JDBC Driver for Oracle Financials Cloud on Windows or /Applications/CData JDBC Driver for Oracle Financials Cloud/ on Mac/Linux).
   • Run the command java -jar cdata.jdbc.oracleerp.jar --license
   • Enter your name, email, and “TRIAL” (or your license key).

5. Configure your connection to Oracle Financials Cloud:

   • Run the command java -jar cdata.jdbc.oracleerp.jar to open the Connection String utility.
   • Configure the connection string and click “Test Connection.”
   • Note: If Oracle Financials Cloud uses OAuth, you will need to authenticate in your browser.
   • Once successful, copy the connection string for use later.

6. Create a .prp file for your JDBC connection (e.g., oracle-financials-cloud.prp):

   Use the following properties and format:

   • Prefix - a prefix to be used for the tools exposed
   • ServerName - a name for your server
   • ServerVersion - a version for your server
   • DriverPath - the full path to the JAR file for your JDBC driver
   • DriverClass - the name of the JDBC Driver Class (e.g., cdata.jdbc.oracleerp.OracleERPDriver)
   • JdbcUrl - the JDBC connection string to use with the CData JDBC Driver to connect to your data (copied from above)
   • Tables - leave blank to access all data, otherwise, you can explicitly declare the tables you wish to create access for

   env Prefix=oracleerp ServerName=CDataOracleERP ServerVersion=1.0 DriverPath=PATHTOcdata.jdbc.oracleerp.jar DriverClass=cdata.jdbc.oracleerp.OracleERPDriver JdbcUrl=jdbc:oracleerp:InitiateOAuth=GETANDREFRESH; Tables=

Integrating with Claude Desktop

1. Create the config file for Claude Desktop (claude_desktop_config.json) to add the new MCP server, using the format below. If the file already exists, add the entry to the mcpServers in the config file.

   Windows

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

   Linux/Mac

   { “mcpServers”: { “{classname_dash}”: { “command”: “/PATH/TO/java”, “args”: [ “-jar”, “/PATH/TO/CDataMCP-jar-with-dependencies.jar”, “/PATH/TO/oracle-financials-cloud.prp” ] }, … } }

   If needed, copy the config file to the appropriate directory (Claude Desktop as the example).

   Windows

   bash cp C:PATHTOclaude_desktop_config.json %APPDATA%Claudeclaude_desktop_config.json

   Linux/Mac

   bash cp /PATH/TO/claude_desktop_config.json /Users/{user}/Library/Application Support/Claude/claude_desktop_config.json’

2. Run or refresh your client (Claude Desktop).

   Note: You may need to fully exit or quit your Claude Desktop client and re-open it for the MCP Servers to appear.

Running the Server Independently

You can also run the MCP Server on its own using the following command:

bash java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/Salesforce.prp

Note: The server uses stdio so can only be used with clients that run on the same machine as the server.

Unleashing the Power of UBOS: Full-Stack AI Agent Development

While the CData MCP Server provides a valuable bridge between Oracle Financials Cloud and LLMs, the UBOS platform takes this integration to the next level. UBOS is a full-stack AI Agent development platform designed to empower businesses to build, orchestrate, and deploy custom AI Agents tailored to their specific needs.

How UBOS Enhances the CData MCP Server Integration:

• Custom AI Agent Development: UBOS allows you to create custom AI Agents that leverage the data accessed through the CData MCP Server. These agents can be designed to automate specific tasks, provide proactive insights, and improve decision-making.
• Multi-Agent Systems: UBOS enables you to build multi-agent systems where multiple AI Agents collaborate to solve complex problems. For example, you could create an agent that monitors financial data for anomalies and another agent that automatically generates reports based on these anomalies.
• Enterprise Data Integration: UBOS provides a seamless way to integrate data from various sources, including Oracle Financials Cloud, into your AI Agents. This allows your agents to access a comprehensive view of your business data.
• LLM Model Integration: UBOS supports the integration of various LLM models, allowing you to choose the best model for your specific use case. You can even use your own custom-trained LLM models.
• Orchestration and Management: UBOS provides tools for orchestrating and managing your AI Agents, ensuring that they are running smoothly and efficiently.

Use Cases with UBOS:

• Automated Financial Analysis: Build an AI Agent that automatically analyzes financial data for trends, anomalies, and opportunities.
• Proactive Risk Management: Create an agent that monitors financial data for potential risks and alerts you to take action.
• Personalized Financial Advice: Develop an agent that provides personalized financial advice to customers based on their individual financial situation.
• Fraud Detection: Build an agent that detects fraudulent transactions in real-time.
• Budgeting and Forecasting: Create an agent that helps you create and manage your budget and forecast future financial performance.

Tools & Descriptions

Once the MCP Server is configured, the AI client will be able to use the built-in tools to read the underlying data. In general, you do not need to call the tools explicitly. Simply ask the client to answer questions about the underlying data system. For example:

• “What is the correlation between my closed won opportunities and the account industry?”
• “How many open tickets do I have in the SUPPORT project?”
• “Can you tell me what calendar events I have today?”

The list of tools available and their descriptions follow:

In the definitions below, {servername} refers to the name of the MCP Server in the config file (e.g. {classname_dash} above).

• {servername}_get_tables - Retrieves a list of tables available in the data source. Use the {servername}_get_columns tool to list available columns on a table. The output of the tool will be returned in CSV format, with the first line containing column headers.
• {servername}_get_columns - Retrieves a list of columns for a table. Use the {servername}_get_tables tool to get a list of available tables. The output of the tool will be returned in CSV format, with the first line containing column headers.
• {servername}_run_query - Execute a SQL SELECT query

Conclusion

The combination of the CData MCP Server for Oracle Financials Cloud and the UBOS AI Agent Development Platform provides a powerful solution for unlocking the value of your financial data. By connecting your data to LLMs like Claude, you can automate tasks, gain insights, and make better decisions. With UBOS, you can take this integration even further by building custom AI Agents that are tailored to your specific business needs.

By leveraging the UBOS platform, businesses can transcend the limitations of generic AI solutions and create intelligent systems that are deeply integrated with their unique data landscape. This enables a new era of data-driven decision-making, where AI Agents work tirelessly to uncover insights, automate processes, and drive business growth.

Start building your own AI Agents today and experience the power of UBOS!