This server provides a tool to retrieve detailed information about work items (requirements) by their ID via the MCP protocol.
Retrieve Work Item Details: Fetch structured JSON data containing the plain text description, image URLs, and raw HTML content of a work item by providing its ID (e.g., YEPPPP-154).
Error Handling: Returns standardized error messages if the external API request fails.
Security: Supports secure handling of sensitive information (organization ID and API token) through environment variables or
.envfiles.Deployment Options: Compatible with Docker deployment for production use.
Development Tools: Provides utilities for local development and testing with features like hot reload.
Agent Integration: Exposes the
get_workitem_descriptiontool that agents can discover and use without needing to handle authentication details.
Supports containerized deployment with various methods for environment variable injection, allowing secure configuration of credentials for production environments.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Workitem Serverget description for workitem YEPPPP-154"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Workitem Server
依赖安装
本项目推荐使用 uv 进行依赖管理和运行。
安装 uv
pip install uv # 或参考 uv 官方文档安装依赖
uv pip install -r requirements.txtRelated MCP server: DataWorks MCP Server
环境变量与配置
推荐使用
.env文件或环境变量注入敏感信息。必需:
organizationId:阿里云组织IDx-yunxiao-token:阿里云API Token
.env 自动加载说明
fastmcp 和 uv 支持自动加载项目根目录下的
.env文件,无需额外代码。启动服务时(如
uv run mcp run mcp_server.py),会自动读取.env文件中的变量。你也可以用 python-dotenv 手动加载(如有特殊需求)。
.env 示例文件
在项目根目录下新建 .env 文件,内容如下:
organizationId=your_org_id
x-yunxiao-token=your_token.env文件用于本地开发和测试,请勿提交敏感信息到代码仓库。建议在
.gitignore文件中加入.env,防止泄漏:# .gitignore .env
Docker 部署与环境变量注入
构建镜像
docker build -t yx-mcp .运行容器(推荐方式)
通过 --env-file 挂载 .env 文件
在项目根目录准备好
.env文件(内容同上)启动容器:
docker run --env-file .env -p 9000:9000 yx-mcp
通过 -e 传递环境变量
直接在命令行传递敏感信息:
docker run -e organizationId=your_org_id -e x-yunxiao-token=your_token -p 9000:9000 yx-mcp
通过 volume 挂载 .env 文件
将本地 .env 文件挂载到容器内:
docker run -v $(pwd)/.env:/app/.env -p 9000:9000 yx-mcp
安全提示: 不要将
.env文件 COPY 进镜像,避免敏感信息泄漏。推荐用--env-file或-e方式传递。
启动服务
# 方式一:直接用环境变量
export organizationId=your_org_id
export x-yunxiao-token=your_token
uv run mcp run mcp_server.py
# 方式二:自动加载 .env 文件(推荐)
uv run mcp run mcp_server.py工具说明
本服务通过 MCP 协议暴露 get_workitem_description 工具,参数为需求ID(如 YEPPPP-154),返回结构化 JSON,包含:
text:纯文本描述images:图片 URL 列表html:原始 HTML 内容
返回示例
{
"id": "YEPPPP-154",
"text": "需求描述文本...",
"images": ["https://...jpg"],
"html": "<div>...</div>"
}错误处理
若外部 API 请求失败,返回
{ "error": "错误信息" },agent 可据此判断。
agent 调用建议
通过 MCP 协议自动发现和调用
get_workitem_description工具。仅需传入
id参数,无需关心 org_id/token。
开发与调试
推荐用
uv run fastmcp dev mcp_server.py进行本地开发,支持热重载和交互测试。支持标准 MCP agent 生态。
参考
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.