Sitecore Design MCP
An MCP server that provides a copywriter agent to automatically enforce predefined copywriting rules for UI text generation. It enables users to process text through a modular rules system to ensure consistency in elements like button labels and error messages.
README
Sitecore Design MCP - Copywriter Agent
A Model Context Protocol (MCP) server with a copywriter agent that enforces copywriting rules for UI text generation. Deployed on Vercel with HTTP transport support.
Overview
This MCP server provides a copywriter tool that processes UI copy text and automatically applies predefined copywriting rules. The agent is designed to be called whenever UI copy is generated or when users ask questions about UI text.
Features
- Copywriter Agent: Automatically enforces copywriting rules on UI text
- Modular Rules System: Easy-to-add rules configuration
- HTTP Transport: Compatible with MCP HTTP client specification
- Vercel Deployment: Pre-configured for seamless Vercel deployment
- Type-Safe: Full TypeScript support with Zod validation
Project Structure
sitecore_design_mcp/
├── app/
│ └── api/
│ └── mcp/
│ └── route.ts # MCP HTTP endpoint
├── lib/
│ ├── mcp-server.ts # MCP server setup
│ └── copywriter/
│ ├── index.ts # Copywriter agent interface
│ ├── rules.ts # Copywriting rules (ADD YOUR RULES HERE)
│ └── processor.ts # Rule processing logic
└── ...
Setup
1. Install Dependencies
npm install
2. Add Your Copywriting Rules
Edit lib/copywriter/rules.ts to add your copywriting rules. Each rule is a function that takes a string and returns a processed string:
export const copywritingRules: CopywritingRule[] = [
(text: string) => {
// Your rule logic here
return processedText;
},
// Add more rules...
];
3. Local Development
npm run dev
The MCP server will be available at http://localhost:3000/api/mcp
4. Deploy to Vercel
Option A: Using Vercel CLI
npm install -g vercel
vercel
Option B: Using Git Integration
- Push your code to a Git repository (GitHub, GitLab, etc.)
- Import the project in the Vercel dashboard
- Vercel will automatically detect Next.js and deploy
Configuration
Environment Variables
Copy .env.example to .env and add any required environment variables:
cp .env.example .env
Cursor Integration
To use this MCP server with Cursor, add the following to your Cursor MCP configuration:
{
"mcpServers": {
"sitecore-design-mcp": {
"url": "https://your-deployment.vercel.app/api/mcp",
"transport": "http"
}
}
}
Replace https://your-deployment.vercel.app with your actual Vercel deployment URL.
Usage
The copywriter tool is automatically available when the MCP server is connected. It can be called:
- Automatically: When UI copy text is generated
- Explicitly: When users ask questions about UI text
Tool Parameters
text(required): The text to process through copywriting rulescontext(optional): Context about where the copy will be used (e.g., "button label", "error message")
Example Tool Call
{
"method": "tools/call",
"params": {
"name": "copywriter",
"arguments": {
"text": "click here to continue",
"context": "button label"
}
}
}
Adding Rules
To add new copywriting rules:
- Open
lib/copywriter/rules.ts - Add your rule function to the
copywritingRulesarray - Add corresponding metadata to
ruleMetadataarray - Rules are applied in sequence, so order matters
Example rule:
export const copywritingRules: CopywritingRule[] = [
// Existing rules...
// New rule: Capitalize first letter
(text: string) => {
if (!text) return text;
return text.charAt(0).toUpperCase() + text.slice(1);
},
];
Development
Scripts
npm run dev- Start development servernpm run build- Build for productionnpm run start- Start production servernpm run lint- Run ESLint
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。