This article introduces the Ardoq MCP server and how it enables AI clients to retrieve real-time, structured data from Ardoq. It explains how the protocol works, what features Ardoq supports, and how to connect to Claude for Desktop, with connection guides to other clients coming soon.
What Is MCP?
The Model Context Protocol (MCP) is an open protocol that standardizes how external tools and data sources can be exposed to large language models (LLMs). MCP acts as a universal adapter between models and tools, allowing AI clients to discover and use tools dynamically, with minimal manual integration.
For example, with MCP, an AI assistant can connect to a system like Ardoq and automatically access up-to-date information, such as lists of projects, reports, or applications. It can then use that context to answer questions, generate summaries, or assist with decision-making. This removes the need for manual copy-pasting or hardcoded API calls, making it easier to bring real-time business data into AI-powered workflows.
Tools and Features
The Ardoq MCP server provides AI assistants with secure, real-time access to your Ardoq data through a growing set of tools. For example, an assistant can list your available reports, run and summarize them, and generate charts or visualizations, all using natural language.
Below are a few examples of how an AI assistant connected to the Ardoq MCP server can interact with your data through natural language.
Example 1: Explore Available Reports
The assistant uses the get_reports tool to retrieve a complete list of reports from the Ardoq workspace.
Example 2: Generate a Detailed Report Summary
In this example, the assistant runs a selected report and returns a summary with key insights like cost, progress, and timelines.
Example 3: Generate a Visual Summary from Multiple BCM Reports
The assistant combines data from multiple business capability reports to generate a visual dashboard showing various metrics.
Ardoq’s MCP tools make it easy to access and work with your data and insights through natural language, without using the Ardoq UI. While current tools are read-only, upcoming support for write operations, human-in-the-loop workflows, and new features such as get_metamodel and populate_viewpoint will enable even more powerful use cases. To suggest additional tools, visit the Ardoq Product Portal via the feedback link in the app.
API Token Guidelines
To authenticate with the Ardoq MCP server, you must provide an API token in the Authorization header. This token should be generated from a service account, not tied to a personal user.
Follow these steps to create a secure and maintainable token for your integration:
1. Create a Service Account in Ardoq
In Ardoq, go to:
Preferences → Access Control → Service accountsClick Create new
Fill in the required fields:
Service account name – e.g.,
Claude MCP AccessToken description – e.g.,
Used by Claude Desktop to access MCP serverService account role – Choose a role with the minimum permissions needed (e.g., read-only access to relevant workspaces)
Click Create service account
Copy and save the generated token securely. This token will be used in the MCP configuration.
You will not be able to view the token again after closing the dialog. Store it securely.
2. Manage Existing Service Accounts
To update or remove a token:
Click the three-dot menu next to the service account name
Select Regenerate token or Delete
Regenerating a token will break any existing integration using the old token.
3. Follow These Security Best Practices
Use service accounts exclusively for MCP integrations
Restrict access to only what’s needed for your use case
Keep the token secret – never hardcode it or commit it to version control. Use environment variables in your config
Using service accounts ensures better security, easier management, and avoids disruptions when team members leave your organization.
Connect Claude Desktop to Your Ardoq MCP Server
This section explains how to configure Claude for Desktop to connect with your Ardoq MCP server, enabling Claude to understand and interact with your Ardoq model data.
Claude Free and Pro licenses require a local proxy for MCP communication using a Node.js module. A Claude Max license enables remote MCP server connections directly. The following example assumes the need for a local proxy.
Prerequisites
Node.js v18 or higher
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. Install Claude for Desktop
Download the app from the official site: claude.ai/download
Choose macOS or Windows.
Follow the installation instructions.
MCP is currently supported only on Claude for Desktop — not on Claude Web.
2. Configure Claude to Use the Ardoq MCP Server
1. Open Claude for Desktop.
2. Click the Claude menu and choose Settings…
3. In the left sidebar, click Developer, then click Edit Config.
This opens or creates a config file at:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
4. Replace the contents with the following block:
{
"mcpServers": {
"ardoq": {
"command": "npx",
"args": [
"mcp-remote",
"https://<your-host>.ardoq.com/mcp/sse",
"--header",
"Authorization:Bearer ${ARDOQ_API_TOKEN}"
],
"env": {
"ARDOQ_API_TOKEN": "<your-token>"
}
}
}
}
Replace:
<your-token>with your Ardoq API token<your-host>with your org hostname
5. Save the file and close your editor.
3. Restart Claude
Fully quit and restart Claude for Desktop.
If everything is set up correctly, you should now see either:
A hammer icon in the input bar. Clicking it will show available tools, including the Ardoq MCP server.
Or
ardoqwill show up under the Search and tools tab in the input bar, with the available tools.
4. Test the Integration
Try prompting Claude with:
"Please show me the reports I have in Ardoq"
If configured correctly, Claude will fetch real-time report from the Ardoq MCP server.
Next, you can try prompting:
"Can you give me more information <insert name of report from the list of reports>"
Claude will then search for that report in your Ardoq org and fetch all the available information.
Allow Access
Claude will ask for permission when it runs an external tool for the first time. You can safely click Allow always.
You're All Set!
Your Claude Desktop is now successfully integrated with the Ardoq MCP server. From here, you can start exploring your Ardoq data through natural conversation. Try fetching reports, generating summaries, and creating visual charts directly from your report content.