UBOS Asset Marketplace: Unleashing the Power of AI with the CData MCP Server for Azure DevOps

In today’s data-driven world, the ability to seamlessly connect and leverage information across various platforms is paramount. The UBOS Asset Marketplace is designed to empower businesses by providing a centralized hub for AI-driven solutions. Among the featured assets, the CData MCP (Model Context Protocol) Server for Azure DevOps stands out as a game-changer for integrating live data into Large Language Models (LLMs) like Claude Desktop.

What is the CData MCP Server for Azure DevOps?

The CData MCP Server for Azure DevOps acts as a bridge between your Azure DevOps data and AI applications. It leverages the CData JDBC Driver for Azure DevOps to expose Azure DevOps data as relational SQL models. This innovative approach allows LLMs to query live data using natural language questions, eliminating the need for complex SQL queries.

Key Features:

• Seamless Integration: Connects Azure DevOps data to LLMs like Claude Desktop with ease.
• Natural Language Queries: Enables querying data using natural language, simplifying data retrieval.
• Live Data Access: Provides real-time access to Azure DevOps data, ensuring up-to-date information.
• SQL Abstraction: Hides the complexity of SQL, making data accessible to non-technical users.
• Read-Only Access: Ensures data integrity with read-only access (read/write beta versions are available).
• Simplified Setup: Streamlined setup process for quick deployment.

Use Cases:

1. Enhanced AI-Powered Reporting: Generate insightful reports and dashboards by querying Azure DevOps data using natural language. Imagine asking Claude Desktop, “What is the correlation between closed won opportunities and account industry?” and receiving a comprehensive analysis without writing a single line of SQL.
2. Improved Project Management: Track project progress, identify bottlenecks, and optimize resource allocation by querying Azure DevOps data in real-time. Ask, “How many open tickets do I have in the SUPPORT project?” to get an instant overview of your team’s workload.
3. Streamlined Decision-Making: Empower decision-makers with instant access to critical information, enabling faster and more informed decisions. Query, “Can you tell me what calendar events I have today?” to stay on top of your schedule and commitments.
4. Automated Data Analysis: Automate data analysis tasks by integrating Azure DevOps data with AI models. This can help identify trends, predict outcomes, and optimize business processes.
5. Custom AI Agent Development: You can use the MCP server as data source for your custom AI Agents.

How the CData MCP Server Works

The CData MCP Server acts as an intermediary, translating natural language queries into SQL queries that can be executed against the Azure DevOps data. Here’s a breakdown of the process:

1. Connection: The server establishes a connection to Azure DevOps using the CData JDBC Driver.
2. Translation: The server translates natural language queries from the LLM into SQL queries.
3. Execution: The server executes the SQL queries against the Azure DevOps data.
4. Response: The server returns the results to the LLM in a structured format.

Setting Up the CData MCP Server

The setup process involves several key steps:

1. Cloning the Repository: Start by cloning the provided GitHub repository containing the necessary files.
2. Building the Server: Use Maven to build the server, creating a JAR file with all dependencies.
3. Installing the JDBC Driver: Download and install the CData JDBC Driver for Azure DevOps.
4. Licensing the Driver: License the JDBC driver using the provided command-line tool.
5. Configuring the Connection: Use the Connection String utility to configure the connection to your Azure DevOps instance. This involves specifying connection properties such as authentication method and credentials.
6. Creating a .prp File: Create a .prp file containing the connection details, including the driver path, driver class, JDBC URL, and table prefixes.
7. Configuring Claude Desktop: Modify the Claude Desktop configuration file (claude_desktop_config.json) to add the new MCP server, specifying the command and arguments required to run the server.
8. Running the Server: Execute the command to start the MCP Server, pointing it to the .prp file.

Understanding the .prp File

The .prp file is crucial for configuring the connection to Azure DevOps. It contains the following properties:

• Prefix: A prefix used for the tools exposed by the server.
• 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.azuredevops.AzureDevOpsDriver).
• JdbcUrl: The JDBC connection string to use with the CData JDBC Driver to connect to your data.
• Tables: Leave blank to access all data, or explicitly declare the tables you wish to create access for.

Integrating with Claude Desktop

To use the CData MCP Server with Claude Desktop, you need to modify the claude_desktop_config.json file. This involves adding a new entry to the mcpServers section, specifying the command and arguments required to run the server. The command should point to your Java executable, and the arguments should include the path to the JAR file and the .prp file.

After modifying the configuration file, you may need to fully exit and reopen Claude Desktop for the MCP Server to appear.

Utilizing the Available Tools

Once the MCP Server is configured, Claude Desktop can use the built-in tools to interact with the underlying data. These tools include:

• {servername}_get_tables: Retrieves a list of tables available in the data source.
• {servername}_get_columns: Retrieves a list of columns for a table.
• {servername}_run_query: Executes a SQL SELECT query.

While you don’t typically need to call these tools explicitly, understanding their functionality is crucial for scripting requests to the server.

Example JSON-RPC Requests

For scripting requests to the MCP Server, you can use JSON-RPC 2.0. Here are some examples:

• Getting Tables:

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

• Getting Columns:

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

• Running a Query:

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

Troubleshooting Common Issues

• Server Not Appearing: Ensure you have fully quit and reopened Claude Desktop.
• Data Retrieval Issues: Verify your connection configuration and ensure the connection string is correct.
• Connection Problems: Contact the CData Support Team for assistance.
• MCP Server Issues: Join the CData Community for support and feedback.

The UBOS Advantage: Powering Your AI Agent Development

While the CData MCP Server for Azure DevOps provides a crucial bridge between your data and LLMs, the UBOS platform elevates your AI initiatives to the next level. UBOS is a full-stack AI Agent development platform focused on empowering businesses to seamlessly integrate AI Agents into every department.

Here’s how UBOS enhances your AI Agent development:

• AI Agent Orchestration: UBOS provides a robust framework for orchestrating AI Agents, allowing you to manage and coordinate their interactions effectively. This ensures seamless collaboration and optimized performance.
• Enterprise Data Connectivity: UBOS simplifies the process of connecting AI Agents to your enterprise data sources. Whether it’s Azure DevOps, CRM systems, or databases, UBOS provides the tools and connectors to ensure seamless data flow.
• Custom AI Agent Building: UBOS empowers you to build custom AI Agents tailored to your specific business needs. You can leverage your own LLM models and integrate them with the UBOS platform to create powerful and intelligent agents.
• Multi-Agent Systems: UBOS supports the development of Multi-Agent Systems, enabling you to create complex AI solutions that can solve intricate business challenges. This allows you to leverage the collective intelligence of multiple agents to achieve your goals.

By combining the CData MCP Server for Azure DevOps with the UBOS platform, you can unlock the full potential of AI and transform your business operations.

Conclusion

The CData MCP Server for Azure DevOps, available on the UBOS Asset Marketplace, represents a significant step forward in integrating live data with AI applications. By simplifying data access and enabling natural language queries, it empowers businesses to leverage the power of AI for enhanced reporting, improved project management, and streamlined decision-making. When combined with the UBOS platform, you can unlock even greater potential and transform your business with custom AI Agents and intelligent automation.

License: MIT License

All Supported Sources (truncated list from original document for brevity): Access, Act CRM, Act-On, Active Directory, ActiveCampaign, Acumatica, Adobe Analytics, Adobe Commerce, ADP, Airtable, AlloyDB, Amazon Athena, Amazon DynamoDB, Amazon Marketplace, Amazon S3, Asana, Authorize.Net, Avalara AvaTax, Avro, Azure Active Directory, Azure Analysis Services, Azure Data Catalog, Azure Data Lake Storage, Azure DevOps, Azure Synapse, Azure Table, Basecamp, BigCommerce, BigQuery, Bing Ads, Bing Search, Bitbucket, Blackbaud FE NXT, Box, Bullhorn CRM, Cassandra, Certinia, Cloudant, CockroachDB, Confluence, Cosmos DB, Couchbase, CouchDB, CSV, Cvent, Databricks, DB2, DocuSign, Dropbox, Dynamics 365, Dynamics 365 Business Central, Dynamics CRM, Dynamics GP, Dynamics NAV, eBay, eBay Analytics, Elasticsearch, Email, EnterpriseDB, Epicor Kinetic, Exact Online, Excel, Excel Online, Facebook, Facebook Ads, FHIR, Freshdesk, FTP, GitHub, Gmail, Google Ad Manager, Google Ads, Google Analytics, Google Calendar, Google Campaign Manager 360, Google Cloud Storage, Google Contacts, Google Data Catalog, Google Directory, Google Drive, Google Search, Google Sheets, Google Spanner, GraphQL, Greenhouse, Greenplum, HarperDB, HBase, HCL Domino, HDFS, Highrise, Hive, HubDB, HubSpot, IBM Cloud Data Engine, IBM Cloud Object Storage, IBM Informix, Impala, Instagram, JDBC-ODBC Bridge, Jira, Jira Assets, Jira Service Management, JSON, Kafka, Kintone, LDAP, LinkedIn, LinkedIn Ads, MailChimp, MariaDB, Marketo, MarkLogic, Microsoft Dataverse, Microsoft Entra ID, Microsoft Exchange, Microsoft OneDrive, Microsoft Planner, Microsoft Project, Microsoft Teams, Monday.com, MongoDB, MYOB AccountRight, MySQL, nCino, Neo4J, NetSuite, OData, Odoo, Office 365, Okta, OneNote, Oracle, Oracle Eloqua, Oracle Financials Cloud, Oracle HCM Cloud, Oracle Sales, Oracle SCM, Oracle Service Cloud, Outreach.io, Parquet, Paylocity, PayPal, Phoenix, PingOne, Pinterest, Pipedrive, PostgreSQL, Power BI XMLA, Presto, Quickbase, QuickBooks, QuickBooks Online, QuickBooks Time, Raisers Edge NXT, Reckon, Reckon Accounts Hosted, Redis, Redshift, REST, RSS, Sage 200, Sage 300, Sage 50 UK, Sage Cloud Accounting, Sage Intacct, Salesforce, Salesforce Data Cloud, Salesforce Financial Service Cloud, Salesforce Marketing, Salesforce Marketing Cloud Account Engagement, Salesforce Pardot, Salesloft, SAP, SAP Ariba Procurement, SAP Ariba Source, SAP Business One, SAP BusinessObjects BI, SAP ByDesign, SAP Concur, SAP Fieldglass, SAP HANA, SAP HANA XS Advanced, SAP Hybris C4C, SAP Netweaver Gateway, SAP SuccessFactors, SAS Data Sets, SAS xpt, SendGrid, ServiceNow, SFTP, SharePoint, SharePoint Excel Services, ShipStation, Shopify, SingleStore, Slack, Smartsheet, Snapchat Ads, Snowflake, Spark, Splunk, SQL Analysis Services, SQL Server, Square, Stripe, Sugar CRM, SuiteCRM, SurveyMonkey, Sybase, Sybase IQ, Tableau CRM Analytics, Tally, TaxJar, Teradata, Tier1, TigerGraph, Trello, Trino, Twilio, Twitter, Twitter Ads, Veeva CRM, Veeva Vault, Wave Financial, WooCommerce, WordPress, Workday, xBase, Xero, XML, YouTube Analytics, Zendesk, Zoho Books, Zoho Creator, Zoho CRM, Zoho Inventory, Zoho Projects, Zuora, … Dozens More