Use Microsoft Copilot Studio to talk to your Microsoft Dataverse Data via CData Connect AI

Cameron Leblanc
Cameron Leblanc
Technology Evangelist
Leverage the CData Connect AI Remote MCP Server to enable Microsoft Copilot Studio to securely answer questions and take actions on your Microsoft Dataverse data for you.

Microsoft Copilot Studio is a no-code/low-code platform for creating AI Agents that can automate tasks, answer questions, and assist with various business processes. When combined with CData Connect AI Remote MCP, you can leverage Copilot Studio to interact with your Microsoft Dataverse data in real-time. This article outlines the process of connecting to Microsoft Dataverse using Connect AI Remote MCP and creating a connection in Copilot Studio to interact with your Microsoft Dataverse data.

CData Connect AI offers a dedicated cloud-to-cloud interface for connecting to Microsoft Dataverse data. The CData Connect AI Remote MCP Server enables secure communication between Microsoft Copilot Studio and Microsoft Dataverse. This allows you to ask questions and take actions on your Microsoft Dataverse data using Microsoft Copilot Studio, all without the need for data replication to a natively supported database. With its inherent optimized data processing capabilities, CData Connect AI efficiently channels all supported SQL operations, including filters and JOINs, directly to Microsoft Dataverse. This leverages server-side processing to swiftly deliver the requested Microsoft Dataverse data.

In this article, we show how to build a agent in Microsoft Copilot Studio to conversational explore (or Vibe Query) your data. The connectivity principals apply to any Copilot agent. With Connect AI you can build workflows and agents with access to live Microsoft Dataverse data, plus hundreds of other sources.

About Microsoft Dataverse Data Integration

CData provides the easiest way to access and integrate live data from Microsoft Dataverse (formerly the Common Data Service). Customers use CData connectivity to:

  • Access both Dataverse Entities and Dataverse system tables to work with exactly the data they need.
  • Authenticate securely with Microsoft Dataverse in a variety of ways, including Azure Active Directory, Azure Managed Service Identity credentials, and Azure Service Principal using either a client secret or a certificate.
  • Use SQL stored procedures to manage Microsoft Dataverse entities - listing, creating, and removing associations between entities.

CData customers use our Dataverse connectivity solutions for a variety of reasons, whether they're looking to replicate their data into a data warehouse (alongside other data sources)or analyze live Dataverse data from their preferred data tools inside the Microsoft ecosystem (Power BI, Excel, etc.) or with external tools (Tableau, Looker, etc.).


Getting Started


Step 1: Configure Microsoft Dataverse Connectivity for Microsoft Copilot Studio

Connectivity to Microsoft Dataverse from Microsoft Copilot Studio is made possible through CData Connect AI Remote MCP. To interact with Microsoft Dataverse data from Microsoft Copilot Studio, we start by creating and configuring a Microsoft Dataverse connection in CData Connect AI.

  1. Log into Connect AI, click Connections and click Add Connection
  2. Select "Microsoft Dataverse" from the Add Connection panel
  3. Enter the necessary authentication properties to connect to Microsoft Dataverse.

    You can connect without setting any connection properties for your user credentials. Below are the minimum connection properties required to connect.

    • InitiateOAuth: Set this to GETANDREFRESH. You can use InitiateOAuth to avoid repeating the OAuth exchange and manually setting the OAuthAccessToken.
    • OrganizationUrl: Set this to the organization URL you are connecting to, such as https://myorganization.crm.dynamics.com.
    • Tenant (optional): Set this if you wish to authenticate to a different tenant than your default. This is required to work with an organization not on your default Tenant.

    When you connect the Common Data Service OAuth endpoint opens in your default browser. Log in and grant permissions. The OAuth process completes automatically.

    Click Save & Test
  4. Navigate to the Permissions tab in the Add Microsoft Dataverse Connection page and update the User-based permissions.

With the connection configured, we are ready to connect to Microsoft Dataverse data from Microsoft Copilot Studio.

Step 2: Connect Microsoft Copilot Studio to CData Connect AI

Follow these steps to add a CData Connect AI MCP connection in Microsoft Copilot Studio:

  1. Under Tools, click Add tool, then click + New Tool.
  2. In the Add Tool window, search for and click CData Connect AI.
  3. In the Connect to CData Connect AI window, click Create to authenticate your connection CData Connect AI using OAuth authentication.
  4. Click Add and configure to add the CData Connect AI Tool to your agent.

Optional: Give the AI Agent context

This step establishes the AI Agent's role and provides context for the conversation through the Instructions property in the Agent. By providing instructions that explicitly informs the agent about its role as an MCP Server expert and lists the available tools, you can enhance the agent's understanding and response accuracy. For example, you can set the System Message to: 

You are an expert at using the MCP Client tool connected which is the CData Connect AI MCP Server. Always search thoroughly and use the most relevant MCP Client tool for each query. Below are the available tools and a description of each:
queryData: Execute SQL queries against connected data sources and retrieve results. When you use the queryData tool, ensure you use the following format for the table name: catalog.schema.tableName
getCatalogs: Retrieve a list of available connections from CData Connect AI. The connection names should be used as catalog names in other tools and in any queries to CData Connect AI. Use the `getSchemas` tool to get a list of available schemas for a specific catalog.
getSchemas: Retrieve a list of available database schemas from CData Connect AI for a specific catalog. Use the `getTables` tool to get a list of available tables for a specific catalog and schema.
getTables: Retrieve a list of available database tables from CData Connect AI for a specific catalog and schema. Use the `getColumns` tool to get a list of available columns for a specific table.
getColumns: Retrieve a list of available database columns from CData Connect AI for a specific catalog, schema, and table.
getProcedures: Retrieve a list of stored procedures from CData Connect AI for a specific catalog and schema
getProcedureParameters: Retrieve a list of stored procedure parameters from CData Connect AI for a specific catalog, schema, and procedure.
executeProcedure: Execute stored procedures with parameters against connected data sources

Step 3: Explore Live Microsoft Dataverse Data with Microsoft Copilot Studio

With the Agent created in Microsoft Copilot Studio and the MCP tool connected, you can now interact with your Microsoft Dataverse data using Microsoft Copilot Studio. The MCP tool allows you to send queries and receive responses from the Microsoft Dataverse data source in real-time.

Open the chat window in your Microsoft Copilot Studio Agent to begin interacting with your Microsoft Dataverse data. You can ask questions, retrieve data, and perform actions on your Microsoft Dataverse data using the MCP tool:

Get CData Connect AI

To get live data access to 300+ SaaS, Big Data, and NoSQL sources directly from your cloud applications, try CData Connect AI today!

Ready to get started?

Learn more about CData Connect AI or sign up for free trial access:

Free Trial

In this article

Related articles