QASphere MCP server

QA Sphere MCP Server is an integration tool that enables Large Language Models (LLMs) to interact directly with QA Sphere test cases. This server implements the Model Context Protocol (MCP) standard to let you discover, summarize, and chat about test cases within AI-powered development environments.

Prerequisites

Before setting up the QA Sphere MCP server, make sure you have:

• Node.js (recent LTS versions)
• QA Sphere account with API access
• API key from QA Sphere (Settings ⚙️ → API Keys → Add API Key)
• Your company's QA Sphere URL (e.g., example.eu2.qasphere.com)

Setup Instructions

The server is compatible with any MCP client. Here's how to configure it for popular clients:

Claude Desktop

1. Navigate to Claude → Settings → Developer → Edit Config
2. Open claude_desktop_config.json
3. Add the QA Sphere configuration to the mcpServers dictionary

Cursor

1. Go to Settings... → Cursor settings → Add new global MCP server
2. Add the QA Sphere configuration

5ire

1. Open 'Tools' and press 'New'
2. Complete the form with:
   • Tool key: qasphere
   • Command: npx -y qasphere-mcp
   • Environment variables (listed in configuration template below)

Configuration Template

For any MCP client, use the following configuration format:

{
  "mcpServers": {
    "qasphere": {
      "command": "npx",
      "args": [
        "-y", "qasphere-mcp"
      ],
      "env": {
        "QASPHERE_TENANT_URL": "your-company.region.qasphere.com",
        "QASPHERE_API_KEY": "your-api-key"
      }
    }
  }
}

Replace the placeholder values with your actual QA Sphere URL and API key.

Using the MCP Server

Once configured, your MCP-enabled AI assistant can:

• Search for test cases in your QA Sphere instance
• Summarize test coverage for specific features
• Answer questions about test scenarios
• Reference test cases directly within your development workflow

The exact interaction will depend on your specific MCP client, but typically you can ask your AI assistant about QA Sphere test cases and it will use this server to retrieve the relevant information.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.