eln-mcp-server
MCP server for automating ELN data management platform form design using Playwright. Enables users to log in, create and manage templates, design forms with components and formulas, and configure data via natural language.
README
ELN MCP Server
ELN 数据管理平台表单设计 MCP Server。
快速开始
1. 安装依赖
cd d:\github\trae\formily\eln-mcp-server
npm install
npx playwright install chromium
2. 编译
npm run build
3. 配置到 AI 客户端
将以下配置添加到你的 AI 客户端的 MCP 配置文件中:
{
"mcpServers": {
"eln-form-design": {
"command": "node",
"args": ["d:\\github\\trae\\formily\\eln-mcp-server\\dist\\index.js"],
"env": {
"ELN_BASE_URL": "http://10.1.228.52:13002/api/v1",
"ELN_USERNAME": "admin",
"ELN_PASSWORD": "qwert123",
"ELN_HEADLESS": "true"
}
}
}
}
4. 各客户端配置文件位置
| AI 客户端 | 配置文件路径 | 格式 |
|---|---|---|
| TRAE | ~/.trae-cn/mcp_config.json |
同上方 JSON |
| Claude Desktop | %APPDATA%\Claude\claude_desktop_config.json |
同上方 JSON |
| Cursor | ~/.cursor/mcp_config.json |
同上方 JSON |
| VS Code (Copilot) | .vscode/mcp.json |
同上方 JSON |
5. 环境变量说明
| 变量 | 默认值 | 说明 |
|---|---|---|
| ELN_BASE_URL | http://10.1.228.52:13002/api/v1 | ELN 服务器 API 地址 |
| ELN_USERNAME | admin | 登录用户名 |
| ELN_PASSWORD | qwert123 | 登录密码 |
| ELN_HEADLESS | true | Playwright 无头模式(false=显示浏览器窗口) |
| ELN_TOKEN_CACHE | (系统临时目录) | Token 缓存文件路径 |
6. Skill 文件部署
Skill 文件位于 d:\github\trae\formily\eln-skills\ 目录。将此目录路径告知 AI 客户端:
- TRAE: 在项目
.trae配置中添加 skills 路径 - Claude Desktop: 放入
~/.claude/skills/目录 - Cursor: 在项目
AGENTS.md中引用路径
使用流程
1. 对 AI 说: "帮我登录 ELN 系统"
→ AI 调用 login 工具
2. 对 AI 说: "创建一个矿渣粉重量分析模板"
→ AI 调用 list_categories → create_template → add_component → add_formula → save_template
3. 对 AI 说: "查看系统里有哪些模板"
→ AI 调用 list_templates
4. 对 AI 说: "修改模板 258 的公式"
→ AI 调用 select_template → list_formulas → add_formula → save_template
工具列表(26 个)
认证(2)
login- 浏览器自动化登录check_auth- 检查 token 有效性
模板管理(5)
create_template- 创建新模板select_template- 选择已有模板copy_template- 复制模板delete_template- 删除模板信息save_template- 保存到服务器
表单设计(7)
add_component- 添加组件(29 种)set_property- 修改组件属性get_schema- 获取当前 Schemaset_full_schema- 直接设置完整 Schemaremove_component- 删除组件list_components- 列出所有组件reset_schema- 重置 Schema
数据配置(5)
add_formula- 添加公式(22 个函数)list_formulas- 列出公式add_output_item- 添加输出值set_detection_date- 设置检测日期get_data_config- 获取数据配置
表格搭建(3)
set_table_template- 设置表格模板get_table_template- 获取表格模板bind_cell_data- 绑定单元格
查询(4)
list_templates- 查询模板列表get_template_detail- 获取模板详情list_categories- 查询分类list_submission_logs- 查询提交日志
Skill 文件
| 文件 | 内容 |
|---|---|
| component-catalog.md | 29 种组件的属性和用法 |
| formily-schema-guide.md | Formily JSON Schema 编写规范 |
| expression-engine.md | 22 个内置函数和公式编写示例 |
| table-building.md | x-spreadsheet 表格搭建指南 |
| form-design-workflow.md | 完整工作流和常见请求处理 |
技术栈
- 运行时: Node.js 18+
- 语言: TypeScript 5.3+
- MCP SDK: @modelcontextprotocol/sdk
- 浏览器自动化: Playwright
- 参数校验: Zod
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.