MCUDebugforAI
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCUDebugforAICompile the firmware, flash it, and single-step to main with registers open."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCUDebugforAI — 给 AI 用的 MCU 编译/调试器
为 AI 智能体设计的 MCU 编译/调试工具(交互习惯参考 Keil uVision 等传统嵌入式 IDE,方便工程师零成本上手):所有能力通过统一 op 接口开放 (CLI / MCP / TCP 自控端口 / GUI 四通道同源),让 AI 能自主完成 编译 → 下载 → 断点 → 采样 → Flash 反读取 的完整调试闭环,人通过 GUI 实时看到 AI 的每一步操作(人机联调同账本)。
功能
编译:Keil UV4 命令行封装,编译日志解析回执
调试:断点(行级/使能失能)、观察点、语句级单步、运行控制、寄存器
采样:断点自动采样循环、运行态 live 采样,数据落盘回执路径+摘要
Flash:反读取(bin+hex 双格式)、与本地固件比对、全片 dump(三重验证门+降速阶梯)
芯片:CPUID 判内核(M0/M3/M4/M7/M33)+ 家族容量寄存器(F1/F4/H7/F7 布局)
符号:DWARF 源码定位(Go To Definition/Reference)、结构体/数组树形展开
源码:文件树、头文件包含展开、单文件/全工程搜索
GUI:调试工作台(参考 Keil uVision 交互习惯:代码阅读器+断点红点+Watch 树+状态总线自动跟随)
Related MCP server: jlink-mcp
双探针后端
后端 | 探针 | 说明 |
J-Link | SEGGER | 全功能首选(pylink 封装) |
pyOCD | ST-Link/CMSIS-DAP | 内存/下载;F4 寄存器建议走 J-Link |
mock | 无 | 无板演示/CI 全链演练 |
快速开始
pip install -r requirements.txt
python selftest.py # 无板自测(应全 PASS)
python main.py # 启动 GUI
python cli.py ai '{"op":"help"}' # AI 冷启动:接口自描述
python mcp_server.py # MCP stdio 服务(工具面自动生成)AI 接入(MCP)
MCP 工具面由 op 注册表自动生成(dbg.connect→dbg_connect)。
AI 冷启动第一调 {"op":"help"} 即可拿到全部可执行示例;
接口唯一权威清单见 docs/API.md。
无板演示
内置 mock 引擎(64KB Flash 模拟+演示固件循环+变量演化), selftest 与 GUI 全链可无板跑通。
商标声明
本工具为独立开发的开源软件,与 ARM、Keil、SEGGER 无任何隶属、合作或背书关系。 Keil、MDK、uVision 为 Arm 及其关联方的商标,SEGGER、J-Link 为 SEGGER Microcontroller 的商标——文中提及仅用于描述本工具的兼容性(指示性使用),不构成对这些商标的 任何权利主张。用户需自行持有相应工具链(Keil MDK、J-Link 驱动等)的合法授权。
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Run, build, and validate firmware on virtual hardware from your AI agent. Hardware knowledge corpus.
Live browser debugging for AI assistants — DOM, console, network via MCP.
Agent Replay Debugger MCP — record every agent step + deterministic replay. Step-debugger for
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables AI agents to debug embedded systems by providing a comprehensive interface for GDB operations across multiple architectures like ARM and x86. It supports remote debugging via gdbserver or QEMU, allowing for detailed inspection of memory, registers, stack frames, and variables.31-
- AlicenseAqualityDmaintenanceEnables AI assistants like Claude to directly debug microcontrollers via JLink, supporting breakpoints, single-step, memory/register access, variable inspection, RTT logging, and firmware flashing.255MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to interact with GDB for debugging via the MCP protocol. Supports setting breakpoints, stepping through code, inspecting memory and registers, and more.86MIT
- AlicenseAqualityDmaintenanceEnables AI tools to perform full-featured embedded microcontroller debugging via pyOCD and CMSIS-DAP probes, including probe management, flashing, breakpoints, register/memory access, fault analysis, and RTT communication.581MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/SingleDemo/MCUDebugforAI'
If you have feedback or need assistance with the MCP directory API, please join our Discord server