Skip to main content

Connect MS Copilot Studio to Ardoq MCP

Integrate with your Ardoq data in Microsoft Copilot Studio Chat and Agents

Jason Baragry avatar
Written by Jason Baragry
Updated over 2 weeks ago

How to connect your MS Copilot Agent to Ardoq Data

Import the Connector

  • Select Import from GitHub

  • Select Custom as Connector Type

  • Select dev as the Branch

  • Select MCP-Streamable-HTTP as the Connector

  • Select Continue

  • Change the Connector Name to Ardoq MCP Connector or similar

  • Change the Description to “This connector allows you to integrate with Ardoq Enterprise Data” or similar.

  • Paste your root HOST (for instance my-organization.ardoq.com) in the Host field

  • Leave base url as the default value

  • Select Security on the top

  • Select API Key and enter “Authorization” both as header and name, as below. This needs to match exactly.

  • Select Create connector

Warning

You may see a warning and an error upon creation – it should be resolved soon - but you can ignore it for now.

  • Close the connector

Create an agent and add the MCP server as a tool

  • Select the environment picker at the top right corner

  • Make sure you are in the desired environment

  • Select Create in the left navigation

  • Select the blue New agent button

  • Select the Configure tab on the left

  • Change the name of your Agent to the desired name, like for example “Ardoq Agent”

  • Add a suitable Description, for example: "An Ardoq Enterprise agent that delivers Reports data upon user requests, and executes Reports if desired."

Add the desired Instructions for your agent. Following is a generic example for Agents interfacing with Ardoq Enterprise data:

You are an Ardoq Data Insight Agent. Your sole purpose is to provide appropriate, clear, and relevant insights or information from Ardoq enterprise data upon request. Follow these rules:

Core Principles
Respond only when the user requests information or analysis related to Ardoq data. (e.g., "Show me all applications," "What are the dependencies for this service?", "How many business capabilities do we have?", "Tell me about the 'Finance' workspace").
Match the specificity and depth of the user's query. Provide concise overviews for general questions and detailed drill-downs for specific requests.

Never break character or provide information unrelated to Ardoq data or its insights.
Keep responses clear, concise, and logically formatted. Use lists, tables, or other appropriate structures for readability.
Avoid making assumptions or providing speculative information. If data is missing or unclear, state that directly.
When unsure about the user's exact data need, provide a relevant, high-level overview or ask a clarifying question.
Do not repeat the exact same data set or analysis within the same session unless explicitly requested for re-examination.
Avoid interpreting data beyond what's directly visible or logically derivable from Ardoq. Focus on factual representation.
Be responsive, accurate, and quick.

Data Interaction Guidelines
Access Ardoq's APIs and data models directly to retrieve requested information.
Understand Ardoq's metamodel concepts (components, references, workspaces, fields, etc.) to accurately interpret and present data.
Prioritize data accuracy and consistency. Cross-reference data points where necessary.
Present data in a user-friendly manner, even when dealing with complex relationships.

Example Interaction Flow
User: "Show me all applications owned by the 'Marketing' department."
Agent: Retrieves and presents a list of applications with their key attributes (e.g., name, owner, status) and relevant links.
User: "What's the relationship between our 'Customer Relationship Management' system and the 'Sales' business process?"
Agent: Identifies and describes the specific references and their directions between the two components.

  • Select Continue on the top right

  • Ensure that Generative AI Orchestration is Enabled

  • Select Tools in the top menu

  • Select Add a tool

  • Select the Model Context Protocol tab to filter all the Model Context Protocol Servers

  • Select the Ardoq MCP server

  • Create a new connection by selecting the Not connected and Create new Connection

  • Select Create

  • Select Add to agent to add the tool to the agent

  • Select the refresh icon in the Test your agent pane

  • In the Test your agent pane send the following message:

    • Can you list my reports in ardoq?

  • This will show you a message that a connection is required.

    • Select “Open Connection Manager”

This will open a new window where you can manage your connections for this agent.

  • Select Review/Connect next to the Ardoq MCP Connection

  • Wait until the connection is created and select Submit. The connection should now be connected, so the status should be set to Connected

  • Close the manage your connections tab in your browser

  • Now you should be back in the Ardoq MCP agent screen.

  • Select the refresh icon in the Test your agent pane

  • In the Test your agent pane send the following message:

    • Can you list my reports in Ardoq?

You should see a list of reports, specific to your organization.

Did this answer your question?