zephyr-squad-server-mcp
An MCP server that enables AI agents to drive Zephyr for Jira (Server/Data Center) test management via ZAPI. It exposes operations for test cycles, folders, executions, test steps, step results, and ZQL search over stdio for use with any MCP client.
README
zephyr-squad-server-mcp
An MCP server that lets an AI agent drive Zephyr for Jira — Server / Data Center (ZAPI), the test-management suite for Jira. It exposes the most common test-management operations (cycles, folders, executions, test steps, step results, ZQL search) as well-described tools over stdio, so it plugs into Claude Desktop, Claude Code, and any other MCP client.
This targets the Server/DC flavor (
/rest/zapi/latest). It is not for Zephyr Squad Cloud, which uses a different JWT-signed API.
Install
The server is published on PyPI and is easiest to run with
uv:
uvx zephyr-squad-server-mcp # run directly, no install
# or
uv tool install zephyr-squad-server-mcp
# or, in a venv
pip install zephyr-squad-server-mcp
Configuration
The connection rides on your Jira instance's authentication (shared by ZAPI and
the Jira core REST API). Configure via environment variables or a .env file
(see .env.example):
| Variable | Required | Default | Description |
|---|---|---|---|
JIRA_URL |
✅ | — | Jira base URL, e.g. https://jira.company.com (no /rest suffix). |
JIRA_PERSONAL_TOKEN |
one of | — | Personal Access Token → Authorization: Bearer … (recommended for DC). |
JIRA_USERNAME + JIRA_PASSWORD |
one of | — | Basic-auth fallback (password or API token). Used only if JIRA_PERSONAL_TOKEN is empty. |
ZEPHYR_API_PATH |
/rest/zapi/latest |
ZAPI base path on the Jira host. | |
ZEPHYR_TIMEOUT |
30 |
Per-request timeout (seconds). | |
ZEPHYR_VERIFY_SSL |
true |
Verify TLS certs. Set false only for trusted internal self-signed hosts. |
The server fails fast with a clear error if the base URL or authentication is missing.
Client configuration (stdio)
Add to your MCP client config (e.g. Claude Desktop claude_desktop_config.json
or Claude Code .mcp.json):
{
"mcpServers": {
"zephyr-squad": {
"command": "uvx",
"args": ["zephyr-squad-server-mcp"],
"env": {
"JIRA_URL": "https://jira.company.com",
"JIRA_PERSONAL_TOKEN": "your-personal-access-token"
}
}
}
}
For local development against a checkout, point command at uv:
{
"mcpServers": {
"zephyr-squad": {
"command": "uv",
"args": ["run", "--directory", "/path/to/zephyr-squad-server-mcp", "zephyr-squad-server-mcp"],
"env": { "JIRA_URL": "https://jira.company.com", "JIRA_PERSONAL_TOKEN": "…" }
}
}
}
Tools
All id-bearing tools accept either a numeric id or a human-friendly
key/name for project (key like SONY or its name), version (name like
Version 1.0, or -1/Unscheduled), and issue (key like SONY-1386).
Resolved ids are cached for the session, so the first call does the lookup and
later calls reuse it.
Full reference: see
docs/tools.mdfor every tool's arguments, types, defaults, the exact ZAPI endpoint it calls, and sync/async behavior. The table below is a quick index.
| Tool | What it does |
|---|---|
list_cycles |
List test cycles for a project/version. |
get_cycle |
Get one cycle's details (id -1 = the Ad hoc cycle). |
create_cycle |
Create a test cycle. |
update_cycle |
Update a cycle's fields (id is sent in the body). |
delete_cycle |
Delete a cycle (async; auto-polls to completion by default). |
export_cycle |
Get a CSV download link for a cycle's executions. |
copy_executions_to_cycle |
Copy executions into a cycle (async; auto-polls to completion by default). |
move_executions_to_folder |
Move executions from a cycle into a folder (async; auto-polls to completion by default). |
list_cycle_folders |
List folders within a cycle. |
create_folder |
Create a folder under a cycle. |
update_folder |
Update a folder's name/description. |
delete_folder |
Delete a folder from a cycle (async; auto-polls to completion by default). |
list_executions |
List executions in a cycle (optionally a folder). |
update_execution |
Set an execution's status (PASS/FAIL/WIP/BLOCKED/…). |
list_test_steps |
List the test steps of a test issue. |
create_test_step |
Add a test step to a test issue. |
list_step_results |
List per-step results for an execution. |
search_executions |
Run a ZQL query and return matching executions. |
get_execution_status_counts |
Status-count rollup for a project/version (by cycle). |
get_execution_status_counts_by_assignee |
Per-assignee status counts for cycle(s). |
list_executions_by_issue |
A single test's executions across all cycles. |
list_execution_defects |
Defects linked to an execution. |
get_tests_by_requirement |
Tests covering requirement(s); flags orphans. |
get_executions_by_test |
Executions for a test (coverage history). |
get_executions_by_defect |
Executions linked to a defect. |
get_defect_statistics |
Per-defect execution/req/test rollups. |
update_test_step |
Edit a test step's action/data/result. |
delete_test_step |
Delete a test step. |
create_execution |
Schedule a test into a cycle. |
add_tests_to_cycle_from_list |
Bulk-add an explicit list of tests to a cycle as new UNEXECUTED executions (async). |
add_tests_to_cycle_from_filter |
Bulk-add tests matched by a saved ZQL filter to a cycle as new UNEXECUTED executions (async). |
add_tests_to_cycle_from_cycle |
Add tests from another cycle as new UNEXECUTED executions (async). |
update_step_result |
Set a step result's status/comment. |
link_execution_defects |
Link Jira defects to executions (async). |
assign_execution |
Assign an execution to a user. |
delete_execution |
Delete an execution by id. |
get_job_progress (helper) |
Manually poll any async job by token. |
list_projects (helper) |
List projects (name → id discovery). |
list_versions (helper) |
List a project's versions (name → id discovery). |
get_zephyr_test_issue_type (helper) |
Discover the Zephyr Test issue-type id per project (use case 1.1). |
Dates use Jira's dd/MMM/yy format (e.g. 4/Dec/12). Execution-status codes:
-1=UNEXECUTED, 1=PASS, 2=FAIL, 3=WIP, 4=BLOCKED, 5=PENDING, 6=APPROVED, 7=CANCELLED.
Development
uv sync # create venv + install deps (incl. dev group)
uv run pytest # unit tests (httpx mocked with respx — no live Jira needed)
uv run ruff check # lint
uv run mcp dev src/zephyr_squad_server_mcp/server.py # MCP Inspector smoke test
docs/getzephyr.apib is the ZAPI API Blueprint used as the
reference for request/response shapes during development. It was retrieved from the
official public documentation at https://getzephyr.docs.apiary.io/ (© SmartBear
Software). An older version is also available in the
zfjdeveloper/zapi-docs repository.
The Inspector (mcp dev) launches the MCP Inspector via npx, so it needs
Node.js / npx on your PATH. The tool list loads without any Jira config, but
invoking a tool builds the client on first use — so set JIRA_URL and
auth (a .env is read automatically) before running tools.
Publishing to PyPI
uv build # produces wheel + sdist in dist/
uv publish --token "$UV_PUBLISH_TOKEN" # or set UV_PUBLISH_TOKEN in the env
Test against TestPyPI first:
uv publish --publish-url https://test.pypi.org/legacy/ --token "$TESTPYPI_TOKEN"
License
MIT — see LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。