ble-toy-mcp-starter
An open-source tutorial and safe code skeleton that enables users to control their own BLE devices from ChatGPT via MCP and Secure MCP Tunnel.
README
BLE Toy MCP Starter
一套面向普通用户与 AI 编程助手的开源教程和安全代码骨架：从本人持有的 iPhone BLE 玩具出发，用官方 App 产生样本、在 Mac 上分析与短时回放，再封装成 MCP，并通过 OpenAI Secure MCP Tunnel 连接到 ChatGPT。
它不内置任何厂商协议，不使用品牌 Logo，也不自动扫描或控制附近设备。每个研究者都 必须从自己的合法设备与自己的抓包重新确认广播名、GATT 字段、最低档测试帧和停止帧。
架构
iPhone 官方 App ──产生单变量样本──> PacketLogger / Mac
↓ 独立分析
iPhone / ChatGPT <──Secure MCP Tunnel── Mac stdio MCP ──BLE──> 自有设备
iPhone 不直接运行 Python MCP。最终控制由 Mac 负责蓝牙；iPhone/ChatGPT 通过官方 隧道间接调用。LightBlue 适合枚举 GATT 和低风险手动回放，PacketLogger 才负责观察 官方 App 实际写入。
阅读顺序
本仓库不会列出或链接任何设备专属研究，也不会把某一品牌的帧当作通用标准。
安装与 dry-run
python3 --version # 必须是 3.10 或更新版本
python3 -m venv .venv
.venv/bin/pip install -e '.[dev]'
.venv/bin/pytest
BLE_DRY_RUN=1 .venv/bin/ble-toy-mcp
macOS 自带的 python3 可能仍是 3.9；版本不足时，先用 Python.org、Homebrew 或你信任
的 Python 管理器安装 3.10+。
真实设备登记
先设置自己观察到的广播名，再由设备所有者在电脑前选择单台设备：
export BLE_DEVICE_NAME='<NAME_OBSERVED_ON_YOUR_DEVICE>'
.venv/bin/ble-toy-enroll
登记命令只显示本机 CoreBluetooth identifier，不自动保存。把它与本人独立抓到的
BLE_WRITE_UUID、BLE_TEST_FRAME、BLE_STOP_FRAMES 放入本地私密环境，绝不能
提交到 GitHub。格式见 .env.example。
MCP 默认只暴露：
ble_status：查找用户登记的那台设备，不改变状态。ble_short_test：运行本地配置的最低档测试帧，硬上限 5 秒，随后重复停止。ble_stop：重复发送所有本地配置的停止帧。
没有批量控制、按名称自动选择第一台设备或无限时长动作。
公开资料
- Apple Bluetooth 开发者页面（PacketLogger）
- MCP 官方 Python SDK
- OpenAI Secure MCP Tunnel
- ChatGPT developer mode 与 MCP apps
License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.