Dexcom + Carb Search

Dexcom + Carb Search

Enables diabetes management by retrieving real-time glucose readings from Dexcom continuous glucose monitors and searching for carbohydrate content of foods to help make informed dietary decisions.

Category
访问服务器

README

Dexcom + Carb Search

A tool that helps people with diabetes make informed decisions by bringing together real-time glucose data and nutritional information.

What This Does

This service connects to two essential data sources:

  1. Your Dexcom glucose monitor - Retrieves your current blood glucose reading and trend information
  2. Nutritional search - Finds carbohydrate content for foods you're considering eating

By combining these capabilities, it provides a clearer picture for managing blood sugar levels throughout the day.

Who This Is For

This tool is designed for individuals managing diabetes who:

  • Use Dexcom continuous glucose monitoring systems
  • Want quick access to their glucose data alongside nutritional information
  • Prefer having relevant health data available in one place

How It Works

The service integrates with the Dexcom Share platform to access your glucose readings and uses web search to find carbohydrate information for specific foods. All data is retrieved on-demand when requested.

Privacy Note: Your Dexcom credentials are stored securely in your session configuration and are only used to authenticate with Dexcom's official servers.

Setup Requirements

You'll need:

  • An active Dexcom account with Share enabled
  • A Bright Data API key for nutritional search functionality
  • A Smithery account for deployment

Getting Started

Local Development

  1. Start the development server:

    uv run dev
    
  2. Test the tools interactively:

    uv run playground
    

Configuration

The service requires four credentials:

  • Dexcom username - Your Dexcom account email
  • Dexcom password - Your Dexcom account password
  • Dexcom region - Either "us" (United States) or "ous" (Outside US)
  • Bright Data API key - For web search functionality

These can be configured either:

  • Through Smithery session settings (recommended for deployment)
  • As environment variables for local testing
  • As parameters when calling the tools directly

Available Capabilities

Read Blood Glucose

Retrieves your most recent glucose reading from Dexcom, including:

  • Current blood glucose level (mg/dL)
  • Trend direction (rising, falling, steady)
  • Timestamp of the reading

Search Carbs

Finds carbohydrate information for specific foods by searching Google. Simply provide the food name, and the tool returns relevant nutritional data from multiple sources.

Deployment

To make this service available through Smithery:

  1. Create a GitHub repository:

    git init
    git add .
    git commit -m "Initial commit"
    git remote add origin https://github.com/YOUR_USERNAME/YOUR_REPO.git
    git push -u origin main
    
  2. Deploy to Smithery at smithery.ai/new

  3. Configure your Dexcom credentials and Bright Data API key in the Smithery session settings

Technical Details

Built using:

  • Smithery CLI for MCP server deployment
  • Dexcom's official Python SDK (pydexcom)
  • Bright Data API for web search
  • FastMCP framework for tool definitions

Server implementation: bg_server.py

Support

For issues or questions about this implementation, please file an issue in this repository.

For Dexcom-related questions, consult Dexcom Support.

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