Siya Dashboard Menu MCP

Siya Dashboard Menu MCP

This MCP server enables managing dashboard menu sections for client configurations via GitHub API, supporting add, update, and remove operations.

Category
访问服务器

README

Siya Dashboard Menu MCP

A Model Context Protocol (MCP) server for managing dashboard menu sections via GitHub API. This server provides focused section management operations for existing client dashboard configurations.

Features

  • Section Management Only: Add, update, and remove individual menu sections
  • GitHub Integration: Direct integration with GitHub API for configuration management
  • Automatic Commits: All changes are automatically committed to the repository
  • Validation: Built-in validation for section structure and uniqueness
  • Error Handling: Comprehensive error messages with helpful suggestions

Installation

npm install siya-dashboard-menu-mcp

Or install globally:

npm install -g siya-dashboard-menu-mcp

Configuration

  1. Create a .env file (or copy from .env.example):
# GitHub Configuration
GITHUB_TOKEN=your_github_personal_access_token
GITHUB_OWNER=syia-ai
GITHUB_REPO=app-insights-v2
GITHUB_CONFIG_PATH=dashboard-config.json

# Logging Configuration
LOG_LEVEL=info
  1. Ensure your GitHub token has repository access to the target repository.

Usage

As MCP Server

Add to your MCP client configuration:

{
  "mcpServers": {
    "siya-dashboard-menu": {
      "command": "siya-dashboard-menu-mcp",
      "args": [],
      "env": {
        "GITHUB_TOKEN": "your_token_here"
      }
    }
  }
}

Direct Usage

# Start the server
npm start

# Development mode
npm run dev

# Build the project
npm run build

# Test the server
npm test

Available Tools

🔹 Add Menu Section

Tool: add_menu_section

Add a new section to an existing client's dashboard menu.

await callTool("add_menu_section", {
  clientName: "onesea",
  section: {
    name: "Performance Analytics",
    link: "https://onesea.siya.com/analytics",
    identifier: "performance-analytics",
    tag: "object"
  }
});

🔹 Update Menu Section

Tool: update_menu_section

Update specific properties of an existing menu section.

await callTool("update_menu_section", {
  clientName: "onesea",
  identifier: "home",
  updates: {
    name: "Dashboard Home",
    link: "https://onesea.siya.com/dashboard"
  }
});

🔹 Remove Menu Section

Tool: remove_menu_section

Remove a section from a client's dashboard menu.

await callTool("remove_menu_section", {
  clientName: "onesea",
  identifier: "old-feature"
});

Section Structure

Each menu section requires these properties:

{
  "name": "Display Name",           // Required: Shown in menu
  "link": "https://example.com",    // Required: Full URL
  "identifier": "unique-id",        // Required: Unique identifier (kebab-case)
  "tag": "object"                   // Required: Section tag (usually "object")
}

Examples

Adding a New Analytics Section

await callTool("add_menu_section", {
  clientName: "onesea",
  section: {
    name: "Fuel Consumption Analytics",
    link: "https://onesea.siya.com/analytics/fuel-consumption",
    identifier: "fuel-consumption-analytics",
    tag: "object"
  }
});

Updating a Section URL

await callTool("update_menu_section", {
  clientName: "onesea",
  identifier: "emissions",
  updates: {
    link: "https://onesea.siya.com/environmental/emissions-tracking"
  }
});

Removing a Deprecated Section

await callTool("remove_menu_section", {
  clientName: "onesea",
  identifier: "legacy-reports"
});

Resources

The server provides helpful resources:

  • dashboard://section/schema: JSON schema for section validation
  • dashboard://examples/section: Example section configurations and usage

Prompts

Interactive guides are available:

  • section_management_guide: Comprehensive guide for section operations
  • section_best_practices: Best practices for section management

Error Handling

The MCP provides detailed error messages:

  • Client not found: Lists available clients
  • Section not found: Shows available section identifiers
  • Duplicate identifier: Prevents conflicts
  • Invalid format: Validates section structure

Best Practices

Naming Conventions

  • Section Names: Clear, descriptive, Title Case
  • Identifiers: kebab-case, descriptive, unique
  • URLs: HTTPS, complete paths, tested for accessibility

Operations

  • Before adding: Verify client exists, plan unique identifier
  • Before updating: Use exact identifier, test new URLs
  • Before removing: Confirm section is obsolete, consider dependencies

Development

# Clone the repository
git clone https://github.com/syia-ai/siya-dashboard-menu-mcp.git
cd siya-dashboard-menu-mcp

# Install dependencies
npm install

# Set up environment
cp .env.example .env
# Edit .env with your GitHub token

# Build the project
npm run build

# Run in development mode
npm run dev

# Test the server
npm test

Requirements

  • Node.js >= 18.0.0
  • GitHub personal access token with repository permissions
  • Access to the target GitHub repository
  • Existing client configurations (this MCP only manages sections, not clients)

License

MIT

Contributing

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

Support

For issues and questions, please use the GitHub Issues page.

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