Bond MCP Server

Bond MCP Server

Enables AI assistants to control Bond Bridge smart home devices including ceiling fans, motorized shades, dimmable lights, and other RF-controlled devices. Provides comprehensive device management and control capabilities through the Bond Local API.

Category
访问服务器

README

Bond MCP Server

A Model Context Protocol (MCP) server that provides tools for controlling Bond Bridge smart home devices. This server enables AI assistants like Claude to interact with ceiling fans, fireplaces, shades, lights, and other RF-controlled devices through Bond Bridge hubs.

Features

  • Device Management: List and get information about all connected Bond devices
  • Fan Control: Control ceiling fan speed, direction, and power state
  • Shade Control: Open, close, and set positions for motorized shades
  • Light Control: Control dimmable lights and brightness levels
  • Custom Actions: Send any Bond API action to devices
  • Bridge Information: Get Bond Bridge status and configuration

Quick Start

Prerequisites

  • Python 3.11 or higher
  • Bond Bridge on your local network
  • Bond API token (obtained from Bond Home app)

Installation

  1. Create and activate virtual environment:

    python3.11 -m venv bond-mcp-env
    source bond-mcp-env/bin/activate  # On Windows: bond-mcp-env\Scripts\activate
    
  2. Install dependencies:

    pip install -r requirements.txt
    
  3. Configure environment:

    cp .env.example .env
    # Edit .env with your Bond Bridge settings
    
  4. Run the server:

    python -m bond_mcp.server
    

Getting Your Bond Token

  1. Open the Bond Home app on your mobile device
  2. Go to Settings → Bond Bridge → Advanced → API
  3. Copy the Local Token (not the Cloud Token)

Configuration

Create a .env file with your Bond Bridge configuration:

# Required: Bond Bridge settings
BOND_TOKEN=your_bond_api_token_here
BOND_HOST=192.168.1.100

# Optional: Connection settings
BOND_TIMEOUT=10.0
BOND_MAX_RETRIES=3
BOND_RETRY_DELAY=1.0

# Optional: Logging
LOG_LEVEL=INFO

Podman Usage

Build and Run

# Build the container
podman build -t bond-mcp-server .

# Run with environment variables
podman run -i --rm \
  -e BOND_TOKEN=your_token_here \
  -e BOND_HOST=192.168.1.100 \
  bond-mcp-server

Available Tools

Device Management

  • list_devices() - List all Bond devices
  • get_device_info(device_id) - Get detailed device information
  • get_device_state(device_id) - Get current device state
  • get_bridge_info() - Get Bond Bridge information

Device Control

  • toggle_device_power(device_id) - Toggle device on/off
  • send_custom_action(device_id, action, argument?) - Send custom Bond action

Fan Control

  • set_fan_speed(device_id, speed) - Set fan speed (0-8)
  • set_fan_direction(device_id, direction) - Set direction ("forward"/"reverse")

Shade Control

  • control_shades(device_id, action, position?) - Control shades
    • Actions: "open", "close", "set_position"
    • Position: 0-100 (for set_position action)

Light Control

  • set_light_brightness(device_id, brightness) - Set brightness (0-100)

MCP Client Integration

Add to your MCP settings:

{
  "mcpServers": {
    "bond": {
      "command": "podman",
      "args": [
        "run", "-i", "--rm",
        "-e", "BOND_TOKEN=your_token_here",
        "-e", "BOND_HOST=192.168.1.100",
        "bond-mcp-server"
      ]
    }
  }
}

Bond API Reference

This server uses the Bond Local API v2:

Troubleshooting

Common Issues

  1. Connection refused: Ensure Bond Bridge IP is correct and accessible
  2. Authentication failed: Verify Bond token is correct (use Local Token, not Cloud Token)
  3. Device not found: Check device ID exists using list_devices()
  4. Action not supported: Verify device supports the action using get_device_info()

Debug Logging

Enable debug logging by setting LOG_LEVEL=DEBUG in your environment.

License

This project is licensed under the MIT License. See the LICENSE file for details.

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