This article explains how to configure GitHub Copilot in Visual Studio Code to connect with your Ardoq MCP server, enabling Copilot to access and interact with your Ardoq model data.
Prerequisites
Visual Studio Code version 1.99 or later
Download VS CodeGitHub Copilot
How to get accessNode.js v18 or higher
To check if VS Code to the latest version, click Check for Updates... in the top left corner. The button will then change to Restart to Update if you have an older version.
If you don’t already have Node.js installed:
Go to nodejs.org/en/download
Download the LTS version for your operating system
Follow the installation instructions
To confirm the installation, open a terminal and run:
node --version
You should see a version number like v18.17.1.
1. Configure Copilot to Use the Ardoq MCP Server
You can configure MCP servers either globally (in your user settings) or per project (via .vscode/mcp.json). This guide uses per-project configuration for better portability and team sharing.
Open your project in Visual Studio Code.
In your project root, create a folder named
.vscode(if it doesn’t already exist).Inside the
.vscodefolder, create a new file namedmcp.json.Paste the following configuration:
{
"inputs": [
{
"type": "promptString"
}
],
"servers": {
"ardoq": {
"command": "npx",
"args": ["mcp-remote", "https://<your-arg>.ardoq.com/mcp/", "--header", "Authorization:Bearer ${ARDOQ_API_TOKEN}"],
"env": {
"ARDOQ_API_TOKEN": "<your-token>"
}
}
}
}Replace:
<your-token>with your Ardoq API token<your-org>with your Ardoq org hostname
5. Save the file.
2. Start the Ardoq MCP Server
Open the
mcp.jsonfile in VS Code.A “Start” button should appear at the top of the server definition block.
Click Start.
This launches the server and initiates tool discovery. Once successful, the Ardoq MCP tools will be available in your Copilot Chat session.
If you don't see a Start button, verify again that VS Code is up to date, and that the .vscode folder containing mcp.json is in the project root folder.
3. Open Copilot Chat and Select the Ardoq Agent
Click the Copilot Chat-icon
in the title bar to open the chat interface.In the chat input, select Agent from the dropdown menu.
4. Test the Integration
In Copilot Chat, try prompting:
“Please show me the reports I have in Ardoq.”
If configured properly, Copilot will query your Ardoq instance and return real-time report data.
Next, you can try prompting:
"Can you give me more information <insert name of report from the list of reports>"
Copilot will then search for that report in your Ardoq org and fetch all the available information.
Allow Access
The first time an MCP tool runs, Copilot may prompt you to confirm. You can safely click Continue to allow it.
You’re All Set!
Your Visual Studio Code Copilot Chat is now connected to the Ardoq MCP server. From here, you can explore your Ardoq data using natural conversation.