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, allowing your AI assistant to act with full project context.
Added Value: A Context-Aware Bridge
By connecting the SQAI MCP to your JetBrains IDE, you create a direct link between GitHub Copilot's Agent mode and your broader project data:
Unified Intelligence: It connects code repositories, user stories, and documentation so Copilot understands the relationship between different project artifacts.
Automated Traceability: Easily perform tasks like automated test generation, impact analysis, or documentation creation directly from the IDE's chat interface.
Continuous Updates: As you update your code or project requirements, the MCP keeps the system model current, ensuring your AI assistant is never working with stale information.
1. Generate Your API Key
You need an authentication key to securely connect your JetBrains IDE 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 JetBrains IDEs, the GitHub Copilot plugin allows you to extend its capabilities by manually adding MCP servers to a local configuration file.
2.1 Access the Configuration
Open your JetBrains IDE (IntelliJ, PyCharm, etc.).
Open the GitHub Copilot Chat window.
Ensure you are in Agent mode.
Click the tools icon ("Configure Tools") at the bottom of the chat window.
Click Add More Tools. This will open your
mcp.jsonconfiguration file.
2.2 Configuration Snippet
Paste the following into the servers object of your mcp.json file. Replace YOUR_TOKEN with the API key you generated in Step 1.
JSON
{
"servers": {
"SQAI-Suite": {
"url": "https://api.sqai-suite.com/mcp",
"requestInit": {
"headers": {
"Authorization": "Bearer YOUR_TOKEN"
}
}
}
}
}
Also see a full config with reference examples:
{
"servers": {
// add your MCP servers configuration here.
// support both local(stdio) and remote(SSE/Streamable HTTP) servers.
// reference: https://docs.github.com/en/copilot/customizing-copilot/extending-copilot-chat-with-mcp?tool=jetbrains
// example:
// "my-mcp-server": {
// "type": "stdio",
// "command": "my-command",
// "args": [],
// "env": {
// "TOKEN": "my_token"
// }
// },
// "github": {
// "url": "https://api.githubcopilot.com/mcp/",
// "requestInit": {
// "headers": {
// "Authorization": "Bearer my_token"
// }
// }
// }
"SQAI-Suite": {
"url": "https://api.sqai-suite.com/mcp",
"requestInit": {
"headers": {
"Authorization": "Bearer YOUR_TOKEN"
}
}
}
}
}
3. How to Use
Verify the Connection: Once the JSON is saved, click the tools icon again in the chat window to see the available SQAI Suite tools (e.g.,
get-test-case,get-work-item).
Interact: Ask Copilot to utilize your SQAI data during your session. Example:
"Based on the Jira ticket for this feature, generate the unit tests using SQAI Suite tools."
Manage Tools: You can enable or disable specific tools from the "Configure Tools" menu to control exactly what context the agent can access.
Additional Resources
This video provides a visual overview of using Agent mode and MCP in JetBrains IDEs, demonstrating how AI can orchestrate tasks across your project's tools.
Troubleshooting
Issue | Potential Cause | Solution |
Server not appearing | Incorrect Chat mode. | Ensure you are specifically in Agent mode. Standard "Ask" or "Chat" modes do not support MCP tool calling. |
Authentication Error | Invalid token format. | Verify your header is exactly |
Connection Timeout | Network/Proxy. | Ensure the URL |
Tools Unresponsive | Initialization error. | Restart the IDE or reload the GitHub Copilot plugin to re-initialize the MCP server discovery process. |