Copilot

Copilot is Microsoft's AI assistant. This destination lets Copilot read data from any source you connect in Dataddo, so you can ask questions about your data in plain language. It works with two Copilot products: Microsoft Copilot Studio agents, which you can publish to Microsoft 365 Copilot and Teams, and GitHub Copilot in Visual Studio Code. Dataddo delivers the data directly to the model and takes care of the rest.

Dataddo handles the whole pipeline for you. It keeps the data fresh, stores it in SmartCache, and serves it through a built-in querying layer. Every answer comes with metadata: technical metadata such as data freshness, and business metadata such as what each table and column means. You do not write any code.

How It Works

On the Data Anywhere and Enterprise plans, Copilot is a destination, and the data comes from the flows you attach to it. On the Data to AI plan, Copilot is an AI Model, and the data comes from the Contexts you attach to it. A Context is data that Dataddo keeps ready to query. When Copilot needs data, Dataddo serves it from SmartCache and returns the rows together with their freshness and business metadata.

Access is authorized with OAuth. You sign in to Dataddo from Copilot once, with your Dataddo email and password. Copilot then keeps the connection active and renews it in the background, so you do not handle any tokens.

What Copilot Can Do with Your Data

Dataddo exposes your data through its data MCP server at https://headless.dataddo.com/mcp-data. The server is a semantic layer: Copilot asks in business terms (customers, invoices, deals), and Dataddo never accepts SQL from the model. The tools fall into these groups:

A flow or Context can be available but not yet queryable. The model can see it as soon as it is attached, but it can query it only after a semantic model covers it. list_flows reports this for each one.

Setup Overview

The steps depend on your Dataddo plan:

• On the Data Anywhere and Enterprise plans, you work with sources, flows and destinations.
• On the Data to AI plan, you work with Contexts and AI Models instead.

1. Create a Copilot authorizer.
2. Make your data available:
   • Data Anywhere and Enterprise: create a Copilot destination that uses the authorizer, then attach one or more flows to it.
   • Data to AI: create a Copilot AI Model that uses the authorizer, then attach one or more Contexts to it.
3. Add the Dataddo MCP server in Microsoft Copilot Studio or in GitHub Copilot, and sign in with your Dataddo account.

After you sign in, Copilot can access every flow or Context attached to an AI destination or AI Model in your Dataddo account, not only the ones attached to Copilot. Their data appears after they run for the first time.

Authorize Connection to Copilot

Authorize the connection so Dataddo can serve your data to Copilot:

1. Go to Authorizers and click Authorize New Service.
2. Select Copilot.
3. Fill in the fields below and click Save. Dataddo validates the connection when you save it.

Make Your Data Available to Copilot

Follow the steps for your plan.

Data Anywhere and Enterprise Plans

1. Go to Destinations, click Create Destination, and select Copilot.
2. Enter a name, choose the authorizer you created, and click Save.
3. Go to Flows and click Create Flow.
4. Add one or more sources.
5. Add the Copilot destination.
6. Set the schedule that keeps the data fresh and click Save.

Data to AI Plan

1. Go to AI Models and add a new one.
2. Select Copilot.
3. Enter a name and choose the authorizer you created.
4. Attach one or more Contexts to the AI Model.
5. Click Save.

Set Up the Connection in Copilot

You can connect from Microsoft Copilot Studio, which builds agents for Microsoft 365 Copilot and Teams, or from GitHub Copilot in Visual Studio Code.

Microsoft Copilot Studio

In Copilot Studio, you add Dataddo as an MCP tool to an agent. You can then publish the agent to Microsoft 365 Copilot and Teams.

Add the MCP Server to Your Agent

1. Open your agent in Copilot Studio and go to the Tools page.

2. Select Add a tool > New tool > Model Context Protocol. The MCP onboarding wizard opens.

3. Fill in the fields:

   Field	Value
   Server name	Dataddo Data Access
   Server description	A short description, for example Business data from Dataddo: flows, entities, metrics and data freshness. The agent uses it to decide when to call Dataddo.
   Server URL	https://headless.dataddo.com/mcp-data

4. Under authentication, select OAuth 2.0, then select Dynamic discovery as the type. Copilot Studio finds the Dataddo sign-in endpoints and registers itself on its own.

5. Select Create, then Next.

6. In the Add tool dialog, select Create a new connection.

Sign In to Dataddo

1. Copilot Studio opens the Dataddo sign-in page.
2. Enter your Dataddo email and password, and complete multi-factor authentication if you are asked to.
3. After you sign in, you return to Copilot Studio. Select Add to agent.

Use It in Microsoft 365 Copilot and Teams

Test the agent in Copilot Studio first, for example by asking "Which flows do I have in Dataddo?". To use it in Microsoft 365 Copilot and Teams, publish the agent, then go to Channels > Teams and Microsoft Copilot. Keep Make agent available in Microsoft Copilot selected and click Add channel. In Microsoft 365 Copilot, type @, select your agent and ask your question.

GitHub Copilot in Visual Studio Code

On Copilot Business and Copilot Enterprise, an organization admin must enable the MCP servers in Copilot policy first.

1. Open the MCP config file: .vscode/mcp.json in your workspace, or your user mcp.json for all workspaces. You can also run MCP: Add Server from the Command Palette.
2. Add the Dataddo server. Only the URL is needed. Do not add headers, because VS Code registers itself with Dataddo automatically.

{
  "servers": {
    "dataddo": {
      "type": "http",
      "url": "https://headless.dataddo.com/mcp-data"
    }
  }
}

3. Start the server from the code lens above it in mcp.json, or run MCP: List Servers. A browser window opens with the Dataddo sign-in page.
4. Enter your Dataddo email and password, and complete multi-factor authentication if you are asked to.
5. Return to VS Code. Open Copilot Chat, switch to Agent mode and select the tools icon. The dataddo server should be listed with its tools.

Troubleshooting

• A flow or Context is missing: attach it to an AI destination or AI Model in the Dataddo account you signed in with, then let it run.
• Copilot Studio cannot create the connection: check that the Server URL is exactly https://headless.dataddo.com/mcp-data and that you selected OAuth 2.0 with Dynamic discovery.
• VS Code does not open the Dataddo sign-in page: check that the server entry has "type": "http" and the exact URL, and that you did not add an Authorization header.
• The connection stops working: the sign-in expired or was revoked. In Copilot Studio, create a new connection for the tool. In VS Code, start the server again and sign in. To reset a VS Code sign-in fully, run Authentication: Remove Dynamic Authentication Providers.
• You see data from the wrong Dataddo account: you signed in with a different account. Remove the connection, then connect again and sign in with the right account.
• A flow or Context is listed but Copilot cannot query it: it is available but no semantic model covers it yet.
• Copilot cannot fetch data: check that the flow has run at least once, so the Context holds data.
• Stale data: review the flow schedule. Dataddo serves the most recent data it has stored for the Context.

Related Articles

• Data Backfilling to Storages
• Write Modes
• Implementation of Batch Ingestion to Data Warehouses
• Network Access Control List (ACL) Configuration
• SSH Tunnelling
• Data Transformations
• Data Quality Firewall