Kintone Development Support MCP Server

Kintone Development Support MCP Server

Enables developers to access kintone API specifications, field type documentation, and development best practices through natural language queries. Supports API request validation and provides comprehensive development guidance for kintone customizations.

Category
访问服务器

README

Kintone Customize Development Support MCP Server

An MCP (Model Context Protocol) server that provides comprehensive development support for kintone customizations, including API specifications, field type documentation, and development tips.

Features

  • 🔍 API Specification Search: Query kintone REST API specifications by endpoint, method, or category
  • 📝 Field Types Documentation: Access detailed information about kintone field types and their properties
  • 💡 Development Tips: Search development best practices and troubleshooting guides
  • Request Validation: Validate API requests against kintone specifications
  • 🔄 Auto-Updates: Automatic synchronization with official kintone documentation via CICD

Installation

Option 1: Install from npm (Recommended)

# Install globally
npm install -g kintone-mcp-server

# Or using pnpm
pnpm add -g kintone-mcp-server

# Or using yarn
yarn global add kintone-mcp-server

# Run the server
kintone-mcp-server

Option 2: Install locally in project

# Install as dependency
npm install kintone-mcp-server

# Run via npx
npx kintone-mcp-server

# Or add to package.json scripts
{
  "scripts": {
    "mcp-server": "kintone-mcp-server"
  }
}

Option 3: Development setup

# Clone the repository
git clone <repository-url>
cd kintone-mcp-server

# Install dependencies
pnpm install

# Build the server
pnpm build

# Start the server
pnpm start

MCP Client Configuration

Add the server to your MCP client configuration (e.g., Claude Desktop):

If installed globally:

{
  "mcpServers": {
    "kintone-dev-support": {
      "command": "kintone-mcp-server"
    }
  }
}

If installed locally:

{
  "mcpServers": {
    "kintone-dev-support": {
      "command": "npx",
      "args": ["kintone-mcp-server"]
    }
  }
}

Development setup:

{
  "mcpServers": {
    "kintone-dev-support": {
      "command": "node",
      "args": ["/path/to/kintone-mcp-server/dist/index.js"]
    }
  }
}

Available Tools

Tool Name Description Parameters
search_api_specs Search kintone API specifications query, category, method
search_field_types Search field type information fieldType, category
search_development_tips Find development guidance query, category, difficulty
get_api_endpoint Get detailed endpoint info endpoint, method
validate_api_request Validate API request format endpoint, method, requestBody
get_update_info Check data update status includeHistory

Available Resources

Resource URI Description
kintone://api/specifications Complete API specification catalog
kintone://api/field-types Field types documentation
kintone://tips/all All development tips

Usage Examples

Search API Specifications

{
  "name": "search_api_specs",
  "arguments": {
    "query": "get records",
    "category": "records"
  }
}

Get Field Type Information

{
  "name": "search_field_types", 
  "arguments": {
    "fieldType": "SINGLE_LINE_TEXT",
    "includeProperties": true
  }
}

Find Development Tips

{
  "name": "search_development_tips",
  "arguments": {
    "query": "performance optimization",
    "category": "performance"
  }
}

Development

Scripts

  • pnpm build - Build TypeScript to JavaScript
  • pnpm test - Run all tests
  • pnpm test:watch - Run tests in watch mode
  • pnpm lint - Run Biome linter
  • pnpm format - Format code with Biome

Project Structure

src/
├── models/           # Data models and interfaces
├── server/           # MCP server core functionality  
├── tools/            # Individual tool implementations
├── services/         # Storage and update services
└── index.ts         # Application entry point

tests/
├── contract/        # MCP protocol compliance tests
├── tools/           # Individual tool tests
├── integration/     # End-to-end scenario tests
├── unit/           # Unit tests
└── performance/    # Performance tests

Testing

The project follows Test-Driven Development (TDD):

  1. Contract Tests: Verify MCP protocol compliance
  2. Tool Tests: Test individual tool functionality
  3. Integration Tests: End-to-end user scenarios
  4. Unit Tests: Component-level testing

Architecture

  • TypeScript: Type-safe development with strict mode
  • MCP SDK: Official Model Context Protocol implementation
  • File Storage: JSON-based data storage for specifications
  • CICD Integration: Automatic updates from official kintone sources
  • Vitest: Fast unit testing framework
  • Biome: Fast linting and formatting

Data Sources

The server automatically synchronizes with official kintone resources:

  • API Specifications: https://github.com/kintone/rest-api-spec
  • Field Types: https://cybozu.dev/ja/kintone/docs/overview/field-types/
  • Development Tips: https://cybozu.dev/ja/kintone/tips/development/

Contributing

  1. Follow the existing TDD workflow
  2. All tests must pass before committing
  3. Use Biome for code formatting
  4. Update documentation for new features

License

UNLICENSED - Private project

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