Zephyr MCP Server

If you already use Zephyr, the zephyr mcp server is the piece that lets your assistant work with it directly. Model Context Protocol (MCP) server for Zephyr Scale test case management with comprehensive STEP_BY_STEP, PLAIN_TEXT, and BDD support.

What the server does

Model Context Protocol server for Zephyr Scale test management, supporting both Jira Cloud and Data Center. Create, read, and manage test cases through the Atlassian REST API with official API-compliant schemas. Access live test case data, example payloads, and file resources through a unified resource system.

• ✅ Jira Cloud & Data Center Support: Seamlessly connects to both Jira Cloud (using API v2) and self-hosted Data Center instances (using API v1) with automatic configuration detection
• ✅ Official API-Compliant Schemas: Tools and data structures match the official Zephyr Scale REST API, ensuring compatibility and reliability
• ✅ Unified Test Case Creation: A single create_test_case tool handles all script types (BDD, Step-by-Step, Plain Text) for a simplified workflow
• ✅ Full Test Lifecycle Management: Comprehensive tools to create, read, delete test cases, and manage test runs, executions, and folders
• ✅ Live Templating System: Use real test cases from your Zephyr instance as templates (zephyr://testcase/KEY) to ensure consistency and correct project-specific fields
• ✅ Unified Resource System: Access live Zephyr data, local files (file://), and built-in examples through a consistent URI-based system

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

• Organization — The Organization tool exposed by this server

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Credentials and setup notes

Configuration is passed through the environment: ZEPHYR_BASE_URL, ZEPHYR_API_KEY, JIRA_USERNAME, JIRA_API_TOKEN, ZEPHYR_API_BASE_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Where it fits

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Zephyr's toolset — Organization — is a fair guide to whether it matches your workflow. It is maintained by Milo0821; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

• Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.