CX TimeFilter MCP Server

CX TimeFilter MCP Server

Provides time filter tools for CX Dashboard integration, allowing users to set predefined time periods, custom date ranges, and manage time-based filtering across dashboard tabs. Supports HTTP-based MCP protocol with optional authentication for seamless integration with MCP-compatible clients like Langflow.

Category
访问服务器

README

CX TimeFilter MCP Server

A Model Context Protocol (MCP) server providing time filter tools for CX Dashboard. This server exposes time filtering functionality that can be used by any MCP-compatible client, including Langflow.

🎯 Features

  • Set Predefined Time Periods: Last Month, Last 7 days, This Quarter, etc.
  • Set Custom Date Ranges: Specify exact start and end dates
  • List Available Periods: Get all supported time periods
  • HTTP-based MCP Protocol: Easy integration with any MCP client
  • Optional Authentication: API key protection
  • Comprehensive Validation: Input validation and error handling

🚀 Quick Start

1. Installation

# Clone or create the project directory
mkdir cx-timefilter-mcp-server
cd cx-timefilter-mcp-server

# Install dependencies
npm install

2. Configuration

# Copy environment template
cp env.example .env

# Edit .env file
PORT=3000
NODE_ENV=development
MCP_API_KEY=your-secret-api-key-here
ALLOWED_ORIGINS=http://localhost:3001,https://your-langflow-instance.com

3. Run the Server

# Development mode
npm run dev

# Production mode
npm start

# Run tests
npm test

4. Verify Installation

# Health check
curl http://localhost:3000/health

# List available tools
curl http://localhost:3000/mcp/tools

# Test a tool (with API key if configured)
curl -X POST http://localhost:3000/mcp/tools/call \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "name": "set_time_period",
    "arguments": {
      "timePeriodName": "Last Month",
      "tabName": "Overview"
    }
  }'

🛠️ Available Tools

1. set_time_period

Set a predefined time period for dashboard tabs.

Parameters:

  • timePeriodName (string): Exact name of the time period
  • tabName (string): Dashboard tab name

Example:

{
  "name": "set_time_period",
  "arguments": {
    "timePeriodName": "Last Month",
    "tabName": "Overview"
  }
}

2. set_custom_date_range

Set a custom date range with specific start and end dates.

Parameters:

  • startDate (string): Start date in YYYY-MM-DD format
  • endDate (string): End date in YYYY-MM-DD format
  • tabName (string): Dashboard tab name

Example:

{
  "name": "set_custom_date_range",
  "arguments": {
    "startDate": "2024-01-01",
    "endDate": "2024-01-31",
    "tabName": "Comparison"
  }
}

3. list_time_periods

List all available predefined time periods.

Parameters: None

Example:

{
  "name": "list_time_periods",
  "arguments": {}
}

🔗 API Endpoints

Endpoint Method Description
/health GET Health check
/mcp/info GET MCP protocol information
/mcp/tools GET List available tools
/mcp/tools/call POST Execute a tool
/mcp POST Full MCP protocol endpoint

🔐 Authentication

The server supports optional API key authentication:

  1. Set API Key: Add MCP_API_KEY=your-secret-key to .env
  2. Include in Requests: Add Authorization: Bearer your-secret-key header
  3. Alternative Formats: ApiKey your-secret-key or Key your-secret-key

🌐 Langflow Integration

Step 1: Add MCP Tools Component

  1. Open your Langflow project
  2. Add an "MCP Tools" component
  3. Configure the connection

Step 2: Configure Connection

{
  "serverName": "CX TimeFilter Server",
  "connectionMode": "HTTP",
  "serverUrl": "http://localhost:3000",
  "apiKey": "your-api-key",
  "endpoints": {
    "tools": "/mcp/tools",
    "call": "/mcp/tools/call"
  }
}

Step 3: Use Tools in Flows

The tools will appear in Langflow and can be used in your AI workflows.

📦 Deployment

Railway (Recommended)

# Install Railway CLI
npm install -g @railway/cli

# Login and deploy
railway login
railway init
railway up

Render

  1. Connect your GitHub repository
  2. Set environment variables
  3. Deploy automatically

Docker

FROM node:18-alpine
WORKDIR /app
COPY package*.json ./
RUN npm install
COPY . .
EXPOSE 3000
CMD ["npm", "start"]

🧪 Testing

# Run built-in tests
npm test

# Manual testing with curl
curl -X POST http://localhost:3000/mcp/tools/call \
  -H "Content-Type: application/json" \
  -d '{
    "name": "list_time_periods",
    "arguments": {}
  }'

📊 Supported Time Periods

Calendar Periods:

  • All Time, Today, Yesterday
  • This Week, Last Week
  • This Month, Last Month
  • This Quarter, Last Quarter
  • This Year, Last Year

Rolling Periods:

  • Last 24 hours, Last 7 days, Last 14 days
  • Last 30 days, Last 90 days, Last 180 days
  • Last 12 Months

Custom Periods:

  • Any date range in YYYY-MM-DD format

🔧 Development

Project Structure

cx-timefilter-mcp-server/
├── src/
│   ├── server.js              # Main server
│   ├── tools/
│   │   └── timefilter.js      # Time filter tools
│   ├── utils/
│   │   └── mcp-protocol.js    # MCP utilities
│   ├── middleware/
│   │   └── auth.js            # Authentication
│   └── test.js                # Test suite
├── package.json
├── .env
└── README.md

Adding New Tools

  1. Create tool definition in src/tools/
  2. Add validation schema
  3. Implement execute function
  4. Export in tools array
  5. Update README

🐛 Troubleshooting

Common Issues:

  1. Port already in use: Change PORT in .env
  2. CORS errors: Update ALLOWED_ORIGINS in .env
  3. Auth failures: Check MCP_API_KEY configuration
  4. Tool not found: Verify tool name matches exactly

Debug Mode:

NODE_ENV=development npm start

📄 License

MIT License - see LICENSE file for details.

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests
  5. Submit a pull request

Ready to integrate with Langflow and start filtering time periods via MCP! 🎉

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选