This MCP server acts as a digital bridge that allows AI assistants to talk directly to Zephyr Scale, a popular tool for managing software tests inside Jira. Instead of a human manually typing out test cases or clicking through Jira menus, this tool lets an AI model handle the heavy lifting of organizing and documenting quality assurance tasks. It makes it easy for developers to automate the creation of test scenarios, search for existing tests, and keep their testing workflow organized without ever leaving their AI-powered workspace. Under the hood, the server provides a comprehensive suite of tools for managing the entire test lifecycle, from initial creation and folder organization to test runs and execution tracking. It is designed to be versatile, supporting both Jira Cloud and Jira Data Center by automatically detecting the environment to ensure it uses the correct Atlassian REST API version. A particularly clever feature is its unified resource system, which allows an AI to pull live test cases from a Jira instance to use as templates via a custom URI scheme. This ensures that any new content generated by the AI remains consistent with existing project standards and specific custom fields. For developers integrating LLMs into their development environments, this server is especially powerful because it uses official API-compliant schemas. This structure helps the AI understand the exact data requirements for various test formats—including BDD (Gherkin), step-by-step, and plain text scripts—which significantly reduces formatting errors. By exposing these capabilities through the Model Context Protocol, the tool transforms a static Jira instance into a dynamic, context-aware database that an AI can query, update, and expand upon in real-time, greatly accelerating the path from initial requirements to verifiable test results.
Category: Developer Tools & Code Intelligence
Tags: atlassian, jira, qa, testing, zephyr scale
npx (which requires no permanent installation) or install it globally via npm. Option 1: npx (Recommended) No installation command is required; you simply reference the package in your configuration. Option 2: Global Installation bash npm install -g zephyr-scale-mcp-server ---claude_desktop_config.json). The server automatically detects your environment based on the ZEPHYR_BASE_URL, but you can explicitly set JIRA_TYPE to "cloud" or "datacenter" in the environment variables if needed.json { "mcpServers": { "zephyr-server": { "command": "npx", "args": ["zephyr-scale-mcp-server@latest"], "env": { "ZEPHYR_BASE_URL": "https://your-company.atlassian.net", "JIRA_USERNAME": "your-email@example.com", "JIRA_API_TOKEN": "your-api-token" } } } }json { "mcpServers": { "zephyr-server": { "command": "npx", "args": ["zephyr-scale-mcp-server@latest"], "env": { "ZEPHYR_BASE_URL": "https://your-jira-server.com", "ZEPHYR_API_KEY": "your-api-token" } } } } Note: If you performed a global npm installation, change "command": "npx" and "args": ["zephyr-scale-mcp-server@latest"] to "command": "zephyr-scale-mcp". ---get_test_case: Retrieve detailed information about a specific test case. * create_test_case: Create test cases (supports STEP_BY_STEP, PLAIN_TEXT, or BDD content). * update_test_case_bdd: Update an existing test case with BDD content. * delete_test_case: Remove a specific test case. Test Run Management * create_test_run: Initialize a new test run. * get_test_run: Get detailed information about a specific test run. * get_test_run_cases: Retrieve test case keys associated with a test run. * add_test_cases_to_run: Add test cases to an existing test run. Test Execution & Search * get_test_execution: Retrieve specific individual test execution results. * search_test_cases_by_folder: Locate test cases within a specific folder. Organization * create_folder: Create a new folder within Zephyr Scale. Resources * zephyr://testcase/YOUR-TEST-CASE-KEY: Fetch real test case data to use as templates. * file:///path/to/file.json: Access local files. * zephyr://examples/...: Access built-in example payloads. ---create_test_case tool to populate Jira with BDD or Step-by-Step instructions. Example: A developer provides a PRD for a "Password Reset" feature. The AI analyzes the requirements and immediately creates five BDD test cases in Zephyr Scale covering successful resets, expired tokens, and mismatched passwords, placing them in the correct "Security" folder./testcase/KEY`) that allows the AI to fetch a "Gold Standard" test case to use as a template. The AI inspects the live structure—including custom fields and folder paths—and ensures all new test cases created during the session match that exact schema. Example: A QA Lead asks the AI: "Look at PROJ-T123 as a template and create three new test cases for the updated Shopping Cart API." The AI fetches the template, copies the custom "Impact" and "Automation Status" fields, and applies them to the three new entries.
search_test_cases_by_folder to identify all relevant tests for a feature and then execute create_test_run followed by add_test_cases_to_run to set up the testing environment in seconds. Example: A user tells the AI: "Create a new Test Run called 'Sprint 42 Regression' and add every test case currently located in the 'CoreCheckout' folder." The AI searches the folder, retrieves the keys, and generates the Test Run automatically.
Part of MCP Servers