lw-ble-mcp
A lightweight Bluetooth Low Energy debug MCP server for AI agents. It provides 21 tools for BLE scanning, connection, GATT read/write, descriptor access, MTU query, notification subscription, device recon, and engine diagnostics.
README
lw-ble-mcp — 轻量级蓝牙调试 MCP Server
lw-ble-mcp 是一个面向 AI Agent 的轻量级蓝牙低功耗(BLE)调试 MCP 服务器。基于 MCP Python SDK(FastMCP)与 bleak 构建,以 lw_ble_* 前缀提供 21 个工具:扫描、连接、GATT 读写、描述符访问、MTU 查询、通知订阅、一键设备侦查(lw_ble_dump)与引擎诊断(lw_ble_engine_status)。
核心特性:连接永不挂死(全部原生调用在专用 I/O 事件循环上运行,带硬超时)· 下划线工具名兼容广泛 MCP 客户端 · 分层测试体系(76 个用例,含真机回环验证)。
工具标识统一使用
lw_ble_前缀与下划线风格:lw(lightweight,轻量级)沿用嵌入式领域惯例(如 lwIP),ble明确标注协议为蓝牙低功耗。命名刻意保持独立命名空间,避免与常见ble_*工具名冲突。
lw-ble-mcp is a lightweight Bluetooth Low Energy (BLE) debug MCP server for AI agents. Built on the MCP Python SDK (FastMCP) and bleak, it exposes 21 tools under the lw_ble_* prefix: scan, connect, GATT read/write, descriptor access, MTU query, notification subscription, one-shot device recon (lw_ble_dump), and engine diagnostics (lw_ble_engine_status).
Key features: connect never hangs (all native calls run on a dedicated I/O event loop with hard timeouts) · underscore tool names for broad MCP-client compatibility · a layered test suite (76 cases, including real-hardware echo-loop verification).
设计要点
| 关注点 | 实现 |
|---|---|
| 连接边界保护 | 全部 bleak 调用跑在独立线程的专用事件循环上,外层用 asyncio.wait_for 包裹,卡死也能真正超时返回 |
| 客户端兼容性 | 工具名一律用下划线(lw_ble_scan),避免点号工具名与部分 MCP 网关冲突 |
| 错误可诊断 | 区分 entity_not_found / operation_timeout / link_not_connected / internal_error 等错误码 |
| 依赖 | 使用最新的 bleak 3.x |
安装
方式一:PyPI 安装(推荐)
pip install lw-ble-mcp
方式二:源码安装
pip install -r requirements.txt
在 Cursor 中配置
编辑全局 C:\Users\Administrator\.cursor\mcp.json(PyPI 安装后可直接用命令名):
{
"mcpServers": {
"ble": {
"type": "stdio",
"command": "ble_mcp",
"args": []
}
}
}
源码运行时把 command 改为你的 Python 路径、args 用模块方式:
{
"mcpServers": {
"ble": {
"type": "stdio",
"command": "D:/DevTools/Python/v314/python.exe",
"args": ["-m", "ble_mcp"]
}
}
}
配置后重启 Cursor。
工具列表
扫描
| 工具 | 说明 |
|---|---|
lw_ble_scan |
启动后台扫描(支持 name_filter / service_uuid),返回 scan_id |
lw_ble_scan_poll |
非阻塞获取扫描结果 |
lw_ble_scan_stop |
提前停止扫描 |
lw_ble_scan_list |
列出所有扫描 |
连接
| 工具 | 说明 |
|---|---|
lw_ble_connect |
连接外设(带硬超时,不挂死),返回 connection_id |
lw_ble_disconnect |
断开连接 |
lw_ble_connection_status |
查询单个连接状态 |
lw_ble_connection_list |
列出所有连接 |
GATT 读写
| 工具 | 说明 |
|---|---|
lw_ble_discover |
枚举服务的特征/描述符 |
lw_ble_read |
读 GATT 特征(返回 base64 + hex) |
lw_ble_write |
写 GATT 特征(data_b64 或 data_hex) |
lw_ble_read_descriptor |
按句柄读 GATT 描述符 |
lw_ble_write_descriptor |
按句柄写 GATT 描述符 |
lw_ble_mtu |
查询协商 MTU |
通知订阅
| 工具 | 说明 |
|---|---|
lw_ble_subscribe / lw_ble_unsubscribe |
订阅/取消订阅通知 |
lw_ble_poll_notifications |
非阻塞拉取通知缓冲 |
lw_ble_wait_notification |
阻塞等待下一条通知 |
lw_ble_subscription_list |
列出订阅 |
设备侦查与引擎诊断
| 工具 | 说明 |
|---|---|
lw_ble_dump |
一键侦查:服务表 + 全部可读特征值 + MTU(单个调用完成设备摸底) |
lw_ble_engine_status |
引擎资源状态:连接/扫描/订阅计数、I/O 线程健康度 |
信号强度(RSSI)通过
lw_ble_scan/lw_ble_scan_poll返回的每个设备记录获取。不提供独立的 RSSI 工具,因为 Windows 的 WinRT API 不支持从已建立连接中读取 RSSI。
测试
测试体系(常规/边界/参数/连接/稳定性/压力)详见 tests/README.md。
pip install -r requirements-dev.txt
pytest # mock 测试(无需硬件)
pytest -m hw # 真机测试(需 HP_RDTS_P 在线)
直接运行(冒烟测试)
python -m ble_mcp
MCP stdio server 会等待 stdin 的协议消息。可用 npx @modelcontextprotocol/inspector python -m ble_mcp 进行图形化调试。
本地开发运行
python -m ble_mcp
相关信息
| 项目 | 值 |
|---|---|
| 模块名 | lw-ble-mcp |
| 作者 | linzhiwei(zevonlin) |
| 邮箱 | zevonlin@gmail.com |
| 日期 | 2026-08-10 |
| PyPI | https://pypi.org/project/lw-ble-mcp/ |
| GitHub | https://github.com/zevonlin/lw-ble-mcp |
| 项目主页 | https://github.com/zevonlin |
| 版本 | v0.1.0 |
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.