Configuring the DAZZM MCP in Copilot

Introduction

The DAZZM MCP (Model Context Protocol) server lets you connect the GitHub Copilot application directly to a DAZZM application. Once the connection is established, Copilot can act in two areas:

• Modify the application by manipulating its definitions (models, pages, workflows, scripts, etc.);
• Read and modify the data contained in the application.

N.B.: This guide covers the standalone GitHub Copilot application (the desktop/mobile application based on Copilot cloud agent) — not the assistant integrated into VS Code. They are two distinct products, with distinct configuration screens. For VS Code, see Configuring the DAZZM MCP in VS Code.

N.B.: The MCP server was designed to be connected to a development environment, where modifying definitions is allowed. See the Choosing the right environment section before connecting to any other environment.

Prerequisites

• Access to your DAZZM organization’s Account application;
• A DAZZM application with a development environment;
• The GitHub Copilot application installed (desktop or mobile);
• A paid Copilot plan (Pro, Pro+, Max, Business or Enterprise). The GitHub Copilot application relies on Copilot cloud agent, which is not available on the free Copilot plan;
• Node.js installed locally (the connection uses npx — required for the desktop application; not applicable if you only use the mobile application, since its sessions run in the cloud).

Steps to follow

1. Generate an API key (Account)

1. Open the Account application;
2. Access the application you want to connect;
3. Access a development environment of that application;
4. Create an API key. You can name it, for example, “Copilot”;
5. Copy the key’s value.

2. Add the server in the application’s settings

1. Open the GitHub Copilot application;
2. Open Settings, then go to MCP servers;
3. Click Add server;
4. Fill in the form:
   • Server name: dazzm-<app-name> — we recommend naming it dazzm- followed by your application’s name, particularly useful if you connect several applications;
   • Type: Local;
   • Command: npx;
   • Arguments: paste the following, replacing <app-name>, <env-name> and <YOUR_API_KEY>:

["-y", "mcp-remote", "https://<app-name>-<env-name>.apps.dazzm.com/api/prod/mcp", "--header", "api-key:<YOUR_API_KEY>"]

5. Leave Environment variables and Timeout at their default values, unless you have a specific reason to change them;
6. Click Add server.

A few notes about this configuration:

• The URL follows the format https://<app-name>-<env-name>.apps.dazzm.com/api/prod/mcp, where <app-name> is the name of your application and <env-name> is the name of the environment you are connecting to — the same URL segment you use to access your application;
• The prod segment in /api/prod/mcp is fixed: it refers to the version of the DAZZM platform, not to your application’s environment. Do not replace it;
• api-key: is followed directly by the key value copied in step 1, with no space;
• These are the same arguments as those used in VS Code’s mcp.json configuration — if you already have a working VS Code configuration, you can copy the args array directly from it.

3. Verify the connection

Once added, the server appears under Configured servers, in the On this device tab, with a green check mark and its toggle enabled — this indicates that Copilot connected to it successfully.

To confirm it works in practice, start a conversation and ask Copilot to perform a simple, read-only action on your DAZZM application (for example, listing its pages or its models).

Troubleshooting

If the server does not show a green check mark, or Copilot cannot use it:

• Confirm that the URL is correct;
• Confirm that the API key is valid and was pasted with no extra space after api-key:;
• Confirm that the arguments were pasted as a valid JSON array (the field accepts either space-separated arguments or a JSON array — use the JSON array form to avoid issues with the URL and the header);
• Confirm that Node.js is installed on the machine running the desktop application;
• Delete and re-add the server if a setting was entered incorrectly — there is currently no inline editing for the arguments of an already-registered server.

Choosing the right environment

The MCP server can act on any environment, but not all uses are equal:

1. Nominal case — development environment. This is what the MCP server was designed for: Copilot can freely manipulate definitions and test data there.
2. Acceptable case — production environment, read-only. It is possible to connect the MCP server to a production environment if the goal is to use its data reading capabilities for analysis.
3. Strongly discouraged case — writing data outside a test environment.

Modifying data through the MCP server

The MCP server is capable of modifying data in a non-test environment, but this is strongly discouraged. Writing through the MCP server bypasses all of the application’s constraints and business rules: data is written directly to the database, which can lead to integrity errors that crash the application.