About aliyun-yunxiao-projex-mcp
An MCP server for managing Alibaba Cloud Yunxiao Projex projects, aimed at teams using Yunxiao. It provides read and write operations for work items, sprints, comments, members, and project metadata, with access restricted to one configured project.
Key features
- 01Read project and member details
- 02Query work items and field settings
- 03Manage work items and comments
- 04Create and inspect sprints
- 05Require confirmation for deletion
Use cases
- 01Review project work items and statuses
- 02Create or update work items
- 03Inspect sprints and project comments
MCP support
Exposes Yunxiao Projex project-management tools to MCP clients over stdio. It authenticates with a Bot Key and operates only on the configured project.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx yunxiao-projex-mcpYUNXIAO_USER_ACCESS_KEY_IDSecretYunxiao Bot AccessKey IDYUNXIAO_USER_ACCESS_KEY_SECRETSecretYunxiao Bot AccessKey SecretYUNXIAO_USER_NAMEYunxiao user display name for self-assignee detection; optional, must match the AccessKey user when setYUNXIAO_API_ORG_IDYunxiao organization IDYUNXIAO_API_PROJECT_IDYunxiao Projex project IDYUNXIAO_API_ENDPOINTYunxiao API endpoint; defaults to devops.cn-hangzhou.aliyuncs.comLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
18Saved tool list · updated 5d ago
This tool takes no parameters.
Details
From the project README云效 Projex 项目管理 MCP
An MCP server for Alibaba Cloud Yunxiao (阿里云云效) Projex project management. It exposes work items, sprints, comments, members and project metadata as MCP tools over stdio.
基于阿里云云效 Projex OpenAPI 的 MCP 服务。使用 YUNXIAO_USER_* Bot Key,所有工具固定作用于 YUNXIAO_API_PROJECT_ID 指定的项目,无法访问其他项目。
安装
从 PyPI 运行,无需本地克隆:
uvx yunxiao-projex-mcp
或安装到本地环境:
uv tool install yunxiao-projex-mcp
本地开发:
uv sync --all-extras
配置
需要以下环境变量:
| 变量 | 必填 | 说明 |
|---|---|---|
YUNXIAO_USER_ACCESS_KEY_ID | 是 | 云效 Bot AccessKey ID |
YUNXIAO_USER_ACCESS_KEY_SECRET | 是 | 云效 Bot AccessKey Secret |
YUNXIAO_API_ORG_ID | 是 | 云效组织 ID |
YUNXIAO_API_PROJECT_ID | 是 | 云效 Projex 项目 ID |
YUNXIAO_API_ENDPOINT | 否 | 默认 devops.cn-hangzhou.aliyuncs.com |
标准 mcpServers 配置(Magpie / Claude Desktop / Cursor 等通用):
{
"mcpServers": {
"yunxiao-projex": {
"command": "uvx",
"args": ["yunxiao-projex-mcp"],
"env": {
"YUNXIAO_USER_ACCESS_KEY_ID": "your-access-key-id",
"YUNXIAO_USER_ACCESS_KEY_SECRET": "your-access-key-secret",
"YUNXIAO_API_ORG_ID": "your-organization-id",
"YUNXIAO_API_PROJECT_ID": "your-project-id",
"YUNXIAO_API_ENDPOINT": "devops.cn-hangzhou.aliyuncs.com"
}
}
}
}
YUNXIAO_API_ENDPOINT 可省略,省略时使用默认值。
本地 .env
从源码运行时,可在项目根目录放置 .env:
YUNXIAO_API_ORG_ID=...
YUNXIAO_API_PROJECT_ID=...
YUNXIAO_API_ENDPOINT=devops.cn-hangzhou.aliyuncs.com
YUNXIAO_USER_ACCESS_KEY_ID=...
YUNXIAO_USER_ACCESS_KEY_SECRET=...
建议执行 chmod 600 .env,并确保 .env 不被提交到版本库。
接入 Codex
codex mcp add yunxiao_projex \
--env YUNXIAO_API_ORG_ID=... \
--env YUNXIAO_API_PROJECT_ID=... \
--env YUNXIAO_USER_ACCESS_KEY_ID=... \
--env YUNXIAO_USER_ACCESS_KEY_SECRET=... \
-- uvx yunxiao-projex-mcp
codex mcp list
等价的 ~/.codex/config.toml 配置:
[mcp_servers.yunxiao_projex]
command = "uvx"
args = ["yunxiao-projex-mcp"]
[mcp_servers.yunxiao_projex.env]
YUNXIAO_API_ORG_ID = "..."
YUNXIAO_API_PROJECT_ID = "..."
YUNXIAO_USER_ACCESS_KEY_ID = "..."
YUNXIAO_USER_ACCESS_KEY_SECRET = "..."
接入 Magpie
该服务发布到官方 MCP Registry 后,名称为 io.github.MrLinWang/aliyun-yunxiao-projex-mcp。在 Magpie 的 Discover 中搜索 yunxiao、projex、aliyun 或 mcp 即可找到,安装时按提示填写环境变量。
也可以直接编辑 Magpie 的 MCP 配置,使用上面的 mcpServers JSON 片段。
工具
只读:get_project、list_project_members、list_workitem_types、list_workitem_fields、list_workitem_statuses、list_workitems、get_workitem、list_workitem_comments、list_sprints、get_sprint。
写入:create_workitem、update_workitem、create_workitem_comment、update_workitem_comment、create_sprint。
删除:delete_workitem、delete_workitem_comment,均要求 confirm=true。
使用约定
assigned_to、owner_ids、participants、trackers、verifier使用项目成员的账号 ID,可通过list_project_members获取。- 创建工作项前先查
list_workitem_types、list_workitem_fields和list_workitem_statuses;必填自定义字段(例如priority)通过custom_fields传入选项 ID。 list_project_members内部固定使用targetType=Space。- 描述和评论默认使用 Markdown;日期使用
YYYY-MM-DD。 - 删除评论和删除工作项会先校验资源属于当前项目,再执行删除;工作项删除为异步生效,列表索引可能需要数秒刷新。
create_workitem_comment默认创建顶级评论,回复评论时才需要传parent_id。
权限限制
- 当前 Bot 角色为“开发机器人”,修改项目字段、管理项目成员会返回 403。
- 不包含工时/预估、附件、工作项关联、工作项动态、项目创建/删除、迭代修改/删除。
- 代码库与流水线不在本服务范围内。
测试
.venv/bin/python -m pytest -m "not live"
YUNXIAO_LIVE_TESTS=1 .venv/bin/python -m pytest -m "live and not live_write"
YUNXIAO_LIVE_TESTS=1 YUNXIAO_LIVE_WRITE_TESTS=1 .venv/bin/python -m pytest -m live_write
写入测试会创建 __mcp_probe__ 临时工作项并在结束时删除;create_sprint 不做线上写入测试,因为云效未提供删除迭代接口。
许可证
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.