
Dual MCP Server for IoT & Memory
Provides two Model Context Protocol servers that enable controlling IoT devices and managing persistent memory storage with semantic search capabilities.
README
MCP Servers for IoT and Memory Management
This repository contains two Model Context Protocol (MCP) servers:
- IoT Device Control MCP Server
- Memory Management MCP Server
IoT Device Control MCP Server
A Model Context Protocol (MCP) server for controlling and monitoring IoT devices such as smart lights, sensors, and other connected devices.
Purpose
This server provides a standardized interface for IoT device control, monitoring, and state management through the Model Context Protocol.
Use Cases
- Home automation
- Industrial IoT monitoring
- Remote device management
- Smart building control systems
Features
- Send commands to IoT devices
- Query device state and status
- Subscribe to real-time device updates
- Support for MQTT protocol
API Tools
send_command
: Send a command to an IoT deviceget_device_state
: Get the current state of an IoT devicesubscribe_to_updates
: Subscribe to real-time updates from a device
Memory Management MCP Server
A Model Context Protocol (MCP) server for persistent memory storage and retrieval using the Mem0 framework.
Purpose
This server enables long-term memory storage and semantic search capabilities through the Model Context Protocol.
Use Cases
- Conversation history storage
- Knowledge management
- Contextual awareness in AI applications
- Persistent information storage
Features
- Save information to long-term memory
- Retrieve all stored memories
- Search memories using semantic search
API Tools
save_memory
: Save information to long-term memoryget_all_memories
: Get all stored memories for the usersearch_memories
: Search memories using semantic search
Getting Started
- Clone this repository
- Install dependencies:
pip install -r requirements.txt
- Create a
.env
file based on the.env.example
template - Run the IoT server:
python iot_mcp_server.py
- Run the Memory server:
python memory_mcp_server.py
Environment Variables
IoT MCP Server
MQTT_BROKER
: MQTT broker address (default: "localhost")MQTT_PORT
: MQTT broker port (default: 1883)HOST
: Server host address (default: "0.0.0.0")PORT
: Server port (default: "8090")TRANSPORT
: Transport type, "sse" or "stdio" (default: "sse")
Memory MCP Server
MEM0_API_KEY
: API key for Mem0 service (optional)MEM0_ENDPOINT
: Endpoint URL for Mem0 service (default: "https://api.mem0.ai")HOST
: Server host address (default: "0.0.0.0")PORT
: Server port (default: "8050")TRANSPORT
: Transport type, "sse" or "stdio" (default: "sse")
Repository Structure
iot_mcp_server.py
- IoT device control MCP server implementationmemory_mcp_server.py
- Memory management MCP server implementationutils.py
- Utility functions used by the serversrequirements.txt
- Package dependencies.env.example
- Template for environment variables configurationREADME.md
- Documentation
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。