zentao_user_mcp
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., "@zentao_user_mcpGet my current user info from ZenTao"
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.
ZenTao User MCP (Python)
一个用 Python 实现的禅道用户管理 MCP 服务。项目通过禅道 API v1 提供 Token 获取、当前用户查询、用户列表查询,以及用户的创建、更新和删除能力;可使用 stdio 或 Streamable HTTP 两种传输方式。
本项目包含创建、更新和删除禅道用户的工具。HTTP 模式没有内置身份认证,默认仅监听127.0.0.1;不要把服务直接暴露到公网。Token 会作为工具调用内容进入 MCP 客户端或模型上下文,只连接你信任的客户端与模型服务。
功能
MCP 工具 | 说明 | 必填参数 |
| 使用服务端环境变量中的账号和密码获取 Token | 无 |
| 获取当前 Token 对应的用户信息 |
|
| 按用户 ID 查询详情 |
|
| 分页查询用户列表 |
|
| 创建用户 |
|
| 更新用户资料 |
|
| 删除用户 |
|
zentao_user_list 可选参数为 page 和 limit;创建与更新工具的完整参数可由 MCP 客户端自动读取。调用写操作前,请先确认所连接的禅道环境和用户 ID。
Related MCP server: Onde Inference MCP Server
环境要求
Python 3.10 或更高版本(推荐 Python 3.12)
可访问的禅道实例,并已启用 API v1
禅道账号具有相应的用户读取或管理权限
仅运行可选示例时需要 Node.js/npm 和对应的大模型 API Key
快速开始
1. 创建虚拟环境并安装依赖
Windows PowerShell:
python -m venv .venv
.\.venv\Scripts\Activate.ps1
python -m pip install --upgrade pip
python -m pip install -r requirements.txtmacOS/Linux:
python3 -m venv .venv
source .venv/bin/activate
python -m pip install --upgrade pip
python -m pip install -r requirements.txt2. 配置禅道连接
复制示例配置:
Copy-Item .env.example .envmacOS/Linux 使用:
cp .env.example .env然后编辑 .env:
ZENTAO_URL=https://zentao.example.com
ZENTAO_ACCOUNT=admin
ZENTAO_PASSWORD=change-meZENTAO_URL 支持以下形式:
https://zentao.example.comhttps://zentao.example.com/zentaohttps://zentao.example.com/zentao/api.php/v1
程序会将前两种形式自动规范化为 API v1 地址。.env 已被 Git 忽略,请勿把真实账号、密码或 API Key 写入 README、源码或提交记录。
stdio 模式
直接运行:
python server_stdio.py在支持 MCP 的客户端中添加服务器。下面是通用 JSON 配置示例,路径需要替换为本机绝对路径:
{
"mcpServers": {
"zentao": {
"command": "C:\\absolute\\path\\.venv\\Scripts\\python.exe",
"args": ["C:\\absolute\\path\\server_stdio.py"]
}
}
}macOS/Linux 将 command 改为虚拟环境中的 .venv/bin/python。服务会从项目根目录加载 .env,不依赖 MCP 客户端的当前工作目录。
Streamable HTTP 模式
启动服务:
python server_http.py默认端点为 http://127.0.0.1:8000/mcp。支持通过环境变量修改监听地址和端口:
MCP_HOST=127.0.0.1
MCP_PORT=8000HTTP 模式没有应用层鉴权。如果确实需要跨机器访问,应部署在可信网络内,并在前置网关配置 TLS、身份认证和访问控制;不要直接使用 0.0.0.0 裸露到公网。
项目结构
.
|-- server_stdio.py # 禅道 MCP stdio 服务
|-- server_http.py # 禅道 MCP Streamable HTTP 服务
|-- zentao/
| |-- client.py # 禅道 API 请求与 URL 规范化
| |-- client_mcp.py # HTTP MCP + 通义千问示例
| `-- am_mcp.py # 高德 MCP 出行规划示例
|-- mcp_stdio_server.py # 最小加法 MCP 示例
|-- mcp_stdio_client.py # stdio + LangChain 示例
|-- mcp_playwright_client.py # Playwright MCP + 智谱示例
|-- requirements.txt # 核心服务依赖
`-- requirements-examples.txt # 可选示例依赖示例不是运行禅道 MCP 服务的必要部分。如需运行它们,先安装额外依赖:
python -m pip install -r requirements-examples.txt再按 .env.example 配置对应变量。Playwright MCP 示例还要求系统已安装 Node.js/npm。
验证
python -m unittest discover -s tests -v
python -m compileall -q server_stdio.py server_http.py zentao单元测试不连接真实禅道,不会创建、修改或删除用户。首次接入真实环境时,建议先使用只读工具验证 URL、权限和返回格式。
常见问题
返回 401 或 403
确认账号密码、Token 以及禅道账号权限正确,并检查实例是否允许 API 访问。
返回 404
确认 ZENTAO_URL 的部署路径。程序默认将纯域名补全为 /zentao/api.php/v1;如果禅道安装在其他子路径,请直接填写完整的 /api.php/v1 地址。
MCP 客户端无法启动 stdio 服务
使用虚拟环境 Python 和 server_stdio.py 的绝对路径,并先在终端中直接运行一次以检查缺失依赖或 .env 配置错误。stdio 协议使用标准输出通信,启动日志会写入标准错误。
许可证
当前仓库尚未附带开源许可证。公开可见不等于允许复制、修改或分发;正式发布前请根据你的授权意图选择并添加 LICENSE。
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
MCP server for mandates, delegation, policy-gated execution, credential grants, and audit.
Manage CloudPepper servers, Odoo instances, backups, and deployments over MCP.
Query SEC EDGAR filings, XBRL financials, and company data through MCP. STDIO & Streamable HTTP.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceIntegrates Telegram user account with MCP, exposing operations like reading and sending messages, managing chats, and more via stdio or SSE transport.Apache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables managing Onde Inference accounts and model catalog operations through MCP tools such as login, app management, model registration, and assignment. Returns structured JSON over stdio for use with any MCP client.Apache 2.0
- AlicenseAqualityBmaintenanceMCP server that serves tools for interacting with a users API over stdio, supporting operations like finding users. It provides a validated configuration and structured logging for building MCP-based user management workflows.224MIT
- FlicenseNot gradedqualityCmaintenanceEnables creation of MCP servers with both stdio and HTTP transports, providing CRUD tools, resources, and prompts for user management, along with a CLI client for testing and integration.-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/AA509-del/zentao_user_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server