dakboard-mcp-server
Enables management of DAKboard digital dashboards, including screens, blocks, devices, loops, and metrics via MCP tools.
README
DAKboard MCP Server
A Model Context Protocol (MCP) server for managing DAKboard digital dashboards - screens, blocks, devices, loops, and metrics.
Quick Start
Option 1: NPX (No install required)
DAKBOARD_API_KEY=your_api_key npx dakboard-mcp-server
Or add to your MCP config (Claude Desktop, Cursor, etc.):
{
"mcpServers": {
"dakboard": {
"command": "npx",
"args": ["dakboard-mcp-server"],
"env": {
"DAKBOARD_API_KEY": "your_api_key"
}
}
}
}
Option 2: Claude Code
claude mcp add --transport stdio dakboard -- npx dakboard-mcp-server
Then set the environment variable in your shell before launching Claude Code:
export DAKBOARD_API_KEY=your_api_key
Tools
Screens
| Tool | Description |
|---|---|
list_screens |
List all DAKboard screens |
get_screen |
Get detailed screen information including settings |
update_screen |
Update screen settings (name, orientation, dimensions, refresh rate) |
Blocks
| Tool | Description |
|---|---|
list_blocks |
List all blocks on a screen |
get_block |
Get detailed block information |
update_block |
Update block position, size, content, and visibility |
visualize_screen_layout |
Visualize spatial layout as ASCII diagram (provide screen_uuid for accurate layout) |
Loops
| Tool | Description |
|---|---|
list_loops |
List all screen loops |
get_loop |
Get loop details including screen rotation |
Devices
| Tool | Description |
|---|---|
list_devices |
List all DAKboard devices |
get_device |
Get detailed device information |
update_device |
Update device settings (name, IP address, assigned screen) |
Metrics
| Tool | Description |
|---|---|
list_metrics |
List all custom metrics |
get_metric |
Get a metric with its data points |
create_metric_data_points |
Create data points for a metric |
delete_metric |
Delete a metric and all its data points |
delete_metric_data_points |
Delete data points at a specific timestamp |
Utility
| Tool | Description |
|---|---|
test_dakboard_connection |
Test server connection and configuration |
Configuration
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
DAKBOARD_API_KEY |
Yes | - | Your DAKboard API key |
TRANSPORT_TYPE |
No | stdio |
Transport mode: stdio or httpStream |
PORT |
No | 3000 |
Port for HTTP server mode |
HOST |
No | 127.0.0.1 |
Host for HTTP server mode |
Getting Your API Key
- Log in to DAKboard
- Go to Settings > API
- Copy your API key
Development
Commands
pnpm install # Install dependencies
pnpm build # Build TypeScript
pnpm dev # Build with watch mode
pnpm test # Run tests
pnpm lint # Lint code
pnpm format # Format code
pnpm validate # Format + lint + test + build (pre-commit check)
pnpm inspect # Build and launch MCP Inspector
CLI Options
npx dakboard-mcp-server --version # Show version
npx dakboard-mcp-server --help # Show help
HTTP Server Mode
For web-based clients, use HTTP transport:
DAKBOARD_API_KEY=your_api_key TRANSPORT_TYPE=httpStream PORT=3000 node dist/index.js
The server will be available at http://127.0.0.1:3000/mcp.
Architecture
Built with:
- FastMCP - MCP server framework
- Zod - Schema validation for tool parameters
- functype - Functional programming (Either for errors, Branded types for IDs)
- ts-builds - Standardized TypeScript build toolchain
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。