The SQAI Suite MCP (Model Context Protocol) server acts as a centralized intelligence layer for your development environment. It connects your code, user stories, and test management tools into a single, real-time understanding of the system under development.
Added Value: A Context-Aware Bridge
By connecting the SQAI MCP to Visual Studio, you create a direct link between your workspace and your broader project data:
Unified Intelligence: It connects code repositories, user stories, and documentation so your AI assistant understands the relationship between different artifacts.
Automated Traceability: Easily perform tasks like automated test generation, impact analysis, or documentation creation without leaving your editor.
Continuous Updates: As you change your code or update a user story, the MCP enables you to keep the system model updated, ensuring your AI is never working with stale information.
1. Generate Your API Key
You need an authentication key to securely connect Visual Studio to the SQAI Platform.
Log in to the SQAI Platform.
Go to the MCP Configuration page: app.sqai-suite.com/mcp.
Generate and copy your unique API Key.
2. Setup Instructions
In Visual Studio, the MCP configuration is managed via a .mcp.json file. You can apply this at the solution level for team sharing or at the user level for personal use.
Important Configuration Note: It is advised to only add the config in one place (locally per project OR globally), otherwise the MCP server may appear twice.
The advantage of solution-level installation is that you can check the configuration into your repository so all team members share the same setup. The API key is never included in this JSON; the inputs array refers to a locally encrypted and stored input unique to each user, making it safe to commit to version control.
2.1 Choose Your Method
Local (Per Solution): Create or update the file
.mcp.jsonin the root of your solution.Global (All Solutions): Create or update the file
.mcp.jsonin your user profile directory:%USERPROFILE%\.mcp.json.
2.2 Configuration Snippet
Paste the following into your .mcp.json file.
Note: Ensure you use underscores (sqai_api_key) for the input ID as hyphens are not supported for parameters in this environment.
JSON
{
"inputs": [
{
"type": "promptString",
"id": "sqai_api_key",
"description": "API key for SQAI MCP",
"password": true
}
],
"servers": {
"SQAI-Suite": {
"type": "http",
"url": "https://api.sqai-suite.com/mcp",
"headers": {
"Authorization": "Bearer ${input:sqai_api_key}"
}
}
}
}3. How to Use
Open Copilot Chat: Open the GitHub Copilot Chat window in Visual Studio.
Enable Agent Mode: Switch the chat mode to Agent.
Authenticate: When prompted on the first run, enter the API key you generated in Step 1.
Select Tools: Click the tools icon (wrench) in the chat window. Visual Studio will automatically recognize SQAI's MCP capabilities; ensure the SQAI-Suite tools are selected.
Interact: Ask Copilot to utilize your SQAI data.
Example: "Based on the user story for this feature, generate the necessary test cases and sync them to our test management tool."
4. Troubleshooting
Issue | Potential Cause | Solution |
Server not appearing | Incorrect Chat mode. | Ensure Copilot Chat is set to Agent mode. Standard chat modes do not support MCP discovery. |
Input ID Errors | Hyphen usage. | Verify the input ID uses underscores ( |
Repeated auth prompts | Config conflict. | Check for |
Connection failed | Network/Proxy restrictions. | Verify access to |
Logs and Debugging | Startup errors. | Check the Output Window (select "GitHub Copilot" from the dropdown) to view connection logs and error messages. |