Zephyr MCP Server

What is Zephyr MCP Server?

A Model Context Protocol (MCP) server for integrating with Zephyr Scale. It allows developers to fetch test cases programmatically using an MCP‑compatible client (e.g., VS Code).

How to use Zephyr MCP Server?

Clone the repository, install dependencies, then configure VS Code MCP settings with the command python and arguments ["zephyr/zephyr.py"]. Set your Zephyr Scale API token in a .env file. The server exposes the get_test_cases tool that accepts project_key, optional folder_id, and max_results.

Key features of Zephyr MCP Server

• Fetch test cases from Zephyr Scale
• Filter by project key and folder ID
• Limit number of results (default 10)

Use cases of Zephyr MCP Server

• Retrieve test cases for a specific project key
• Filter test cases by a particular folder ID
• Limit test case results to a manageable number
• Integrate test case data into AI‑powered workflows

FAQ from Zephyr MCP Server

How do I set my Zephyr Scale API token?

Create a .env file in the project root and add ZEPHYR_API_TOKEN=your_api_token_here.

How do I configure the server in VS Code?

Add the following to your VS Code MCP settings JSON: {"mcpServers": {"zephyr": {"command": "python", "args": ["zephyr/zephyr.py"]}}}.

What tool does the server provide?

The server provides a single tool called get_test_cases for fetching test cases from Zephyr Scale.

What parameters does get_test_cases accept?

It requires project_key (e.g., "SM"), optionally accepts folder_id (a folder ID to filter test cases), and max_results (maximum number of test cases, default 10).