mingdao-mcp-server
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., "@mingdao-mcp-server list all worksheets in my app"
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.
明道云 MCP Server
MCP (Model Context Protocol) Server for Mingdao (明道云) Worksheet API
📦 GitHub Repository • 🐛 Issues • 👥 Contributors
功能
列出工作表
获取工作表结构(字段、视图)
查询记录(支持筛选、排序、分页)
创建/更新/删除记录
批量操作
关联记录查询与管理
Related MCP server: mdymcp
安装
NPX 运行(推荐,无需安装)
最简单的方式 - 项目已发布到 npm,可直接使用 npx 运行,无需全局安装:
npx mingdao-mcp-server全局安装
如果需要频繁使用,可以全局安装:
npm install -g mingdao-mcp-server从源码安装
git clone <repository-url>
cd mingdao-mcp-server
npm install
npm run build配置
通过环境变量
创建 .env 文件:
# 必需
MINGDAO_APP_KEY=your_app_key
MINGDAO_SIGN=your_sign
# 可选(默认 cooperation.uniontech.com)
MINGDAO_BASE_URL=https://cooperation.uniontech.com使用
快速启动(推荐)
使用 npx 直接运行:
MINGDAO_APP_KEY=your_app_key MINGDAO_SIGN=your_sign npx mingdao-mcp-server全局安装后使用
MINGDAO_APP_KEY=your_app_key MINGDAO_SIGN=your_sign mingdao-mcp-server开发模式
npm run dev生产模式(从源码)
npm startMCP Inspector 调试
npm run inspectorClaude Code 配置
方式一:使用 NPX(推荐,最简单)
在 ~/.claude.json 中配置,无需全局安装:
{
"mcpServers": {
"mingdao": {
"command": "npx",
"args": ["mingdao-mcp-server"],
"env": {
"MINGDAO_APP_KEY": "your_app_key",
"MINGDAO_SIGN": "your_sign",
"MINGDAO_BASE_URL": "https://cooperation.uniontech.com"
},
"type": "stdio"
}
}
}方式二:全局安装
如果已全局安装,使用命令名:
{
"mcpServers": {
"mingdao": {
"command": "mingdao-mcp-server",
"args": [],
"env": {
"MINGDAO_APP_KEY": "your_app_key",
"MINGDAO_SIGN": "your_sign",
"MINGDAO_BASE_URL": "https://cooperation.uniontech.com"
},
"type": "stdio"
}
}
}方式三:从环境变量读取
将环境变量添加到 ~/.zshrc 或 ~/.bashrc:
export MINGDAO_APP_KEY="your_app_key"
export MINGDAO_SIGN="your_sign"
export MINGDAO_BASE_URL="https://cooperation.uniontech.com"然后配置(无需在 JSON 中重复设置环境变量):
{
"mcpServers": {
"mingdao": {
"command": "npx",
"args": ["mingdao-mcp-server"],
"type": "stdio"
}
}
}方式四:本地开发
如需本地开发,使用本地路径:
{
"mcpServers": {
"mingdao": {
"command": "node",
"args": ["/path/to/mingdao-mcp-server/dist/index.js"],
"env": {
"MINGDAO_APP_KEY": "your_app_key",
"MINGDAO_SIGN": "your_sign",
"MINGDAO_BASE_URL": "https://cooperation.uniontech.com"
},
"type": "stdio"
}
}
}环境变量
变量名 | 必需 | 说明 |
| 是 | 明道云应用 Key |
| 是 | API 签名 |
| 否 | 明道云域名,默认 |
Tools
基础操作
list_worksheets- 列出所有工作表get_worksheet_schema- 获取工作表结构
记录 CRUD
query_records- 查询记录(支持筛选、排序、分页)get_record- 获取单条记录create_record- 创建记录update_record- 更新记录delete_record- 删除记录
工作表管理
create_worksheet- 创建新的工作表
关联记录
get_related_records- 获取关联记录create_record_with_relations- 创建记录并建立关联update_record_relations- 更新关联关系
批量操作
batch_create_records- 批量创建batch_update_records- 批量更新
字段类型对照表
类型值 | 字段类型 | 值格式示例 |
2 | 文本 |
|
6 | 数值 |
|
10 | 多选 |
|
11 | 单选 |
|
14 | 附件 |
|
15 | 日期 |
|
16 | 日期时间 |
|
26 | 成员 |
|
29 | 关联记录 |
|
创建工作表示例
{
"name": "任务管理",
"alias": "task",
"controls": [
{
"controlName": "任务标题",
"alias": "title",
"type": 2,
"required": true
},
{
"controlName": "状态",
"alias": "status",
"type": 11,
"required": true,
"strDefault": "待处理"
},
{
"controlName": "优先级",
"alias": "priority",
"type": 2,
"required": false
}
]
}测试
使用测试脚本验证服务器:
# 设置环境变量后测试
MINGDAO_APP_KEY=xxx MINGDAO_SIGN=xxx node test-server.js许可证
MIT
Available Tools
13 toolsbatch_create_recordsC
批量创建多条记录
Inputs: worksheetId (required), records (required).
batch_update_recordsB
批量更新多条记录的相同字段
Inputs: worksheetId (required), rowIds (required), data (required).
create_recordC
在工作表中创建新记录
Inputs: worksheetId (required), data (required).
create_record_with_relationsB
创建新记录并同时建立与其他记录的关联关系
Inputs: worksheetId (required), data (required), relations.
create_worksheetB
创建新的工作表
Inputs: name (required), controls (required), alias.
delete_recordC
删除指定记录
Inputs: worksheetId (required), rowId (required).
get_recordB
根据ID获取单条记录的详细信息
Inputs: worksheetId (required), rowId (required).
get_worksheet_schemaA
获取工作表的字段结构、视图信息,包括所有字段的ID、名称、类型、是否必填等
Inputs: worksheetId (required).
list_worksheetsB
获取应用中的所有工作表列表,包括工作表ID、名称、别名等信息
Inputs: no named parameters.
query_recordsA
按条件查询工作表记录,支持分页、排序、筛选条件
Inputs: worksheetId (required), viewId, pageSize, pageIndex, +3 more.
update_recordC
更新指定记录的字段值
Inputs: worksheetId (required), rowId (required), data (required).
update_record_relationsB
更新记录的关联关系(全量覆盖)
Inputs: worksheetId (required), rowId (required), relations (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 13 tools
Each tool has a clearly distinct purpose: individual vs batch record operations, with/without relations, and worksheet management. There is no ambiguity between create_record and batch_create_records, or between get_record and query_records.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., create_record, batch_create_records, get_worksheet_schema). No mixing of styles or conventions.
13 tools is well-scoped for a data management server, covering record CRUD, batch operations, relations, and worksheet schema. No tool is superfluous, and the count supports a typical workflow.
Core record operations are fully covered, including relations. Minor gaps: missing batch delete, worksheet update/delete, and relation deletion. However, the essential create, read, update, delete, and query are present.
Maintenance
Related MCP Connectors
MCP server for AI dialogue using various LLM models via AceDataCloud
Hosted Airtable MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Official Fibery MCP server: query and update your workspace from any AI client via OAuth.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables AI assistants to search, read, create, and update Feishu/Lark documents and wiki pages. It facilitates seamless document management and wiki searches through OAuth-authenticated API access.MIT
- AlicenseCqualityCmaintenanceUnified MCP server for Mingdao platform, providing 98 tools for collaboration APIs (v1) and HAP gateway. Enables AI IDEs to interact with Mingdao's features like schedules, workflows, knowledge bases, etc.5048 PyPI5MIT
- AlicenseCqualityDmaintenanceMCP server that enables AI agents to control all DingTalk features (messaging, calendar, tasks, approvals, etc.) via natural language using the DingTalk Workspace CLI.831Apache 2.0
- AlicenseNot gradedqualityCmaintenanceMCP server for Feishu/Lark API integration, enabling AI agents to send messages, manage groups, create and edit documents and spreadsheets, and search knowledge bases.MIT