The SQAI Suite MCP (Model Context Protocol) server acts as a centralized intelligence layer for your development environment. By integrating it with GitHub.com, you enable the GitHub Copilot coding agent to autonomously interact with your software's lifecycle, test cases, and user stories directly on the platform.
Added Value: A Context-Aware Bridge
Connecting the SQAI MCP to GitHub.com extends the agent's reasoning capabilities beyond just your code:
Unified Intelligence: It connects code repositories, user stories, and documentation so the GitHub coding agent understands the relationship between different artifacts.
Automated Traceability: Enable the agent to perform tasks like automated test generation, impact analysis, or documentation creation during its autonomous coding sessions.
Continuous Updates: As the agent makes changes or processes new issues, the MCP ensures it remains aligned with the most current system model.
1. Generate Your API Key
You need an authentication key to securely connect the GitHub coding agent 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
For GitHub.com, the configuration is managed within the repository settings. This allows the agent to use your SQAI tools when working on issues or within Copilot Spaces.
2.1 Configure the Environment and Secret
Navigate to your repository on GitHub.com.
Go to Settings > Environments.
Click New environment and name it
copilot. (If this environment already exists, simply click to configure it).Under Environment secrets, click Add environment secret.
Name:
COPILOT_MCP_SQAI_TOKENValue: Paste the API key you generated in Step 1.
2.2 Configure the MCP Server
In your repository settings, go to Copilot > Coding agent.
Locate the MCP configuration section.
Paste the following JSON snippet and click Save.
JSON
{
"mcpServers": {
"SQAI-Suite": {
"type": "http",
"url": "https://api.sqai-suite.com/mcp",
"headers": {
"Authorization": "Bearer $COPILOT_MCP_SQAI_TOKEN"
},
"tools": ["*"]
}
}
}3. How to Use
Initiate a Task: You can now use the MCP server for any actions Copilot takes in your repository from Copilot Spaces or by assigning an issue to the Coding Agent.
Autonomous Interaction: When the agent starts a session, it will automatically recognize the SQAI capabilities and use them as needed to fulfill the task (e.g., pulling user story context to write code).
Learn More: For deep dives into extending agents, check out the official GitHub documentation: Extending Copilot coding agent with MCP.
Troubleshooting
Issue | Potential Cause | Solution |
Agent ignores SQAI tools | Tools not allowlisted. | Ensure the |
Authentication Error | Secret name mismatch. | Verify the secret in your environment is exactly |
Server not active | Environment name. | Ensure the GitHub environment is named exactly |
Connection failed | Network restrictions. | Verify the repository has permission to access external URLs. Large organizations may have firewall policies restricting MCP traffic. |