mdm-mcp
Click on "Deploy 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., "@mdm-mcplist forms under the employee management menu"
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.
mdm-mcp
DEM MDM 的 MCP 服务:12 个 MCP Tools 直连 MDM 后端 API,供 Cursor / Agent 调用。
mdm-worker为遗留 REST 封装,本 MCP 项目不依赖它。
安装与构建
cd mdm-mcp
npm install
npm run build
npm testRelated MCP server: mendix-mcp-server
环境变量
变量 | 必填 | 说明 |
| 是 | MDM 账号 |
| 是 | 已加密密文 |
| 否 | MDM 后端地址,默认 |
| 否 | 租户 ID,默认 |
| 否 | 已有 |
| 否 | HTTP 模式端口,默认 |
运行模式
stdio(默认,供 Cursor 使用)
npm startHTTP(Streamable HTTP,供远程客户端)
npm run start:http服务地址:http://localhost:3100/mcp
HTTP 鉴权(Token 优先)
全部 12 个工具统一支持 Token 优先鉴权,优先级如下:
请求头
token或demdmtoken工具参数
token(未在 schema 暴露,保留兼容)环境变量
MDM_TOKEN环境变量
MDM_ACCOUNT+MDM_PWD(登录获取 token)
典型用法:先调用 mdm_app_menu 获取 token,后续 HTTP 请求在 Header 中携带同一 token,跳过重复登录:
curl -X POST http://localhost:3100/mcp \
-H "Content-Type: application/json" \
-H "token: <demdmtoken>" \
-H "mcp-session-id: <session-id>" \
-d '{ ... }'stdio 模式(Cursor)无 HTTP 请求头,可使用 MDM_TOKEN 环境变量,或由 mdm_app_menu 返回的 token 通过上述回退链自动登录。
Cursor 配置
在 Cursor 的 MCP 设置(mcp.json)中添加:
{
"mcpServers": {
"mdm": {
"command": "node",
"args": ["D:/cloudflare/mdm-mcp-poc/mdm-mcp/dist/index.js"],
"env": {
"MDM_API_BASE_URL": "http://47.92.222.148:30038",
"MDM_TENANT_ID": "779760045352058880",
"MDM_ACCOUNT": "<your-account>",
"MDM_PWD": "<encrypted-pwd>"
}
}
}
}请将 args 路径改为你本机实际路径。
MCP 工具列表(12 个)
Tool | 说明 |
| 应用菜单树 |
| 按菜单名查表单列表(带标签) |
| 表单详情(带标签) |
| 表单原始数据 |
| 子表数据 |
| 表单配置与状态 |
| 表单组件配置 |
| 自定义树父节点 |
| 关联字段分页 |
| 新增/编辑表单 |
| 菜单表单与功能 |
| 岗位人员查询 |
项目结构
src/
services/ # MDM API 业务逻辑(自 mdm-worker 复制)
tools/ # MCP tool 定义与执行
auth.ts # 鉴权(account/pwd 或 token)
config.ts # 环境变量
index.ts # 入口(stdio / HTTP)开发
npm run dev # stdio 调试
npm run dev:http # HTTP 调试This server cannot be deployed
Maintenance
Related MCP Connectors
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
100+ MCP tools for AI agents: content metadata, trade intelligence, business-expertise analysis.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables file system operations, web scraping, and AI-powered search through MCP tools for use by LLM agents.1-
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to read and modify Mendix application models through MCP tools for creating modules, entities, pages, microflows, deploying, and querying runtime data.1-
- AlicenseAqualityDmaintenanceExposes Azure AI Foundry agents, workflows, and AI Search vector-database capabilities as MCP tools, enabling natural language interaction with agents, semantic search, and index management.102MIT
- AlicenseAqualityFmaintenanceProvides 14 MCP tools for AI agent infrastructure, enabling knowledge base queries, skill search, handoffs, blueprint validation, trust scoring, identity verification, SLA validation, and compliance checks.22MIT