Sandbox
@Adancurusul/embedded-debugger-mcp

MCP server for embedded debugging and agent skills

This repository exposes embedded debug operations as MCP tools, with backends for probe-rs and OpenOCD. The same tool set covers probe discovery, target control, memory, breakpoints, flash, RTT, and crash diagnosis, and the CLI can install the bundled skill for Codex and Claude Code.

183 stars28 forksRustUpdated 2mo ago
Who it's for

Builders who want their agent to inspect, flash, and debug connected microcontrollers from a single workflow.

What it delivers

You can diagnose crashes, read memory, flash firmware, and control targets without leaving your agent workflow.

What it does

Two debug backends

Connects through native `probe-rs` or through an OpenOCD GDB remote session, chosen at connect time.

Embedded MCP tool set

Provides tools for listing probes, connecting to a target, halting, stepping, resetting, reading memory, setting breakpoints, and disconnecting.

Flash and RTT support

Includes flash erase, program, verify, run-firmware, and RTT attach/read/write tools for supported targets.

Crash diagnosis tools

Adds `diagnose_fault` and `unwind_exception` for Cortex-M fault evidence and source-line backtraces.

CLI and skill installer

Offers commands for doctor checks, config generation and validation, probe listing, MCP serving, and skill installation.

Packaged Codex and Claude Code skill

Ships a reusable skill under `skills/embedded-debugger/` and a Claude plugin package under `.claude-plugin/`.

How to get it

  1. 1Nightly Rust plus rust-src for the bundled STM32 demo firmware check.
    git clone https://github.com/adancurusul/embedded-debugger-mcp.git
    cd embedded-debugger-mcp
    cargo build --release
  2. 2Run the server explicitly
    embedded-debugger-mcp serve
  3. 3The bundled skill lives in
    skills/embedded-debugger/
  4. 4Install the skill for Codex and Claude Code
    embedded-debugger-mcp skill install --target both
  5. 5Preview or automate the install with JSON
    embedded-debugger-mcp skill install --target both --dry-run --json
    embedded-debugger-mcp skill install --target both --force --json
  6. 6Trigger the Codex skill with a prompt such as
    Use $embedded-debugger to inspect my embedded target setup.

README

Embedded Debugger MCP Server

Rust RMCP License

Embedded Debugger MCP is a Rust server for embedded debugging through either probe-rs (native) or OpenOCD (via the GDB Remote Serial Protocol). It exposes a single MCP tool set for AI assistants — probe discovery, target control, memory, breakpoints, flash, RTT, and AI-facing crash diagnosis — plus a small CLI and bundled skill for a command-driven workflow without setting up an MCP client first.

Language versions: English | 中文

What It Provides

  • One MCP tool set over two interchangeable backends (probe-rs native, or OpenOCD via GDB RSP), chosen at connect. Validated on real ESP32-S3.
  • MCP tools for probe discovery, target connection, core control, memory access, breakpoints, flash programming, RTT communication, and crash diagnosis (diagnose_fault, unwind_exception).
  • CLI commands for environment checks, configuration inspection, probe listing, MCP serving, and skill prompt handoff.
  • A Codex/Claude Code compatible skill at skills/embedded-debugger.
  • Release checks covering rustfmt, clippy, tests, docs, packaging, and the STM32 demo build.

Architecture

MCP client or CLI
        |
        v
embedded-debugger-mcp  (one MCP tool set)
        |
        v
DebugBackend:  probe-rs (native)  |  OpenOCD (GDB RSP)
        |
        v
debug probe / openocd  ->  target MCU

Requirements

  • Rust stable toolchain.
  • A probe-rs compatible debug probe such as ST-Link, J-Link, DAPLink, Black Magic Probe, or a supported FTDI-based probe. Alternatively, a running openocd exposing its GDB port (e.g. openocd-esp32 for ESP32) to use the openocd backend.
  • A supported target chip and working SWD/JTAG wiring for hardware operations.
  • Nightly Rust plus rust-src for the bundled STM32 demo firmware check.

Build

git clone https://github.com/adancurusul/embedded-debugger-mcp.git
cd embedded-debugger-mcp
cargo build --release

The binary is target/release/embedded-debugger-mcp.

MCP Mode

Run the server explicitly:

embedded-debugger-mcp serve

For compatibility, running embedded-debugger-mcp without a subcommand also serves MCP over stdio.

Example MCP client configuration:

{
  "mcpServers": {
    "embedded-debugger": {
      "command": "/path/to/embedded-debugger-mcp/target/release/embedded-debugger-mcp",
      "args": ["serve"],
      "env": {
        "RUST_LOG": "info"
      }
    }
  }
}

On Windows, use the .exe path and Windows path separators.

CLI And Skill Mode

CLI mode is useful for setup checks, automation, and agent workflows before an MCP client is configured.

embedded-debugger-mcp doctor
embedded-debugger-mcp doctor --json
embedded-debugger-mcp probes list
embedded-debugger-mcp probes list --json
embedded-debugger-mcp config generate
embedded-debugger-mcp config validate
embedded-debugger-mcp config show
embedded-debugger-mcp skill print-prompt
embedded-debugger-mcp skill install --target both

The bundled skill lives in:

skills/embedded-debugger/

It is written as a plain Codex skill and is also packaged for Claude Code with .claude-plugin/plugin.json. The skill starts with CLI checks and uses MCP tools only when an MCP client is available.

Install the skill for Codex and Claude Code:

embedded-debugger-mcp skill install --target both

Preview or automate the install with JSON:

embedded-debugger-mcp skill install --target both --dry-run --json
embedded-debugger-mcp skill install --target both --force --json

--target accepts codex, claude, or both. The command installs the Codex skill under ~/.codex/skills/embedded-debugger, the Claude Code skill under ~/.claude/skills/embedded-debugger, and a local Claude plugin-dir package under ~/.claude/plugins/local/embedded-debugger-mcp. Existing directories are not replaced unless --force is passed.

Trigger the Codex skill with a prompt such as:

Use $embedded-debugger to inspect my embedded target setup.

Load the installed Claude Code plugin package:

claude --plugin-dir ~/.claude/plugins/local/embedded-debugger-mcp --print '/embedded-debugger inspect my embedded target setup'

For skill-only environments, the same skills/embedded-debugger directory can also be copied to a local skills directory.

Validate the skill package:

python3 .github/scripts/validate_skill.py skills/embedded-debugger
python3 ~/.codex/skills/.system/skill-creator/scripts/quick_validate.py skills/embedded-debugger
claude plugin validate .
embedded-debugger-mcp skill install --target both --home /tmp/embedded-debugger-skill-home --force --json

The first command validates the repository skill metadata, the second validates the standard SKILL.md layout when the Codex skill creator validator is installed, and the third validates the Claude Code plugin manifest.

Backends

The tools run over one of two interchangeable engines, selected at connect:

  • backend: "probe-rs" (default) — native probe-rs; full flash and RTT support.
  • backend: "openocd" (experimental) — connects to an already-running openocd over its GDB port (openocd_address, default 127.0.0.1:3333) using the GDB Remote Serial Protocol. Intended for targets probe-rs does not cover (e.g. Xtensa ESP32 via openocd-esp32). Memory access and halt/run/step/reset are validated on real ESP32-S3; flash and RTT are probe-rs only. Register reads currently use ARM gdb register numbers, so PC/SP are wrong on Xtensa (known limitation); diagnose_fault and unwind_exception are Cortex-M specific. Start openocd with gdb_memory_map disable, otherwise it probes flash on the GDB connect, fails, and rejects the connection — e.g. openocd -f board/esp32s3-builtin.cfg -c "gdb_memory_map disable".

The AI sees the same tool set for both; only connect arguments change.

MCP Tool Set

Probe management:

ToolPurpose
list_probesDiscover connected debug probes.
connectOpen a probe session for a target chip.
probe_infoShow active session information.

Target control:

ToolPurpose
haltHalt core execution.
runResume execution.
resetReset the core. Only the implemented hardware-style reset path is accepted.
stepSingle-step one instruction.
get_statusRead core/session status.
disconnectDrop the session and clean up resources.

Memory and breakpoints:

ToolPurpose
read_memoryRead target memory with configured size/range limits.
write_memoryWrite target memory when enabled by configuration.
set_breakpointSet a hardware breakpoint.
clear_breakpointClear a hardware breakpoint.

Diagnostics:

ToolPurpose
diagnose_faultRead the Cortex-M SCB fault registers (CFSR/HFSR/MMFAR/BFAR/SHCSR/CPUID) plus PC/SP/LR in one call and return a compact structured evidence bundle with the set fault bits. Reports raw evidence; it does not assert a root cause. Halt the target first.
unwind_exceptionUnwind the stack after a crash and map each frame to a source line. On the probe-rs backend, returns a full DWARF backtrace (function + file:line per frame) via probe-rs's own unwinder; on the OpenOCD backend, reads the Cortex-M exception stack frame and maps the faulting PC / caller LR to source lines. Needs elf_path to firmware built with debug info (.debug_line).

Flash:

ToolPurpose
flash_eraseErase flash when erase permissions are enabled.
flash_programProgram ELF, HEX, or BIN files through probe-rs flash algorithms.
flash_verifyCompare raw expected data with target flash contents.
run_firmwareErase, program, reset/run, and optionally attach RTT.

RTT:

ToolPurpose
rtt_attachAttach to a SEGGER RTT control block.
rtt_detachDetach RTT.
rtt_channelsList discovered RTT channels.
rtt_readRead from an up channel with max byte and timeout limits.
rtt_writeWrite to a down channel.

Crash Diagnosis

After a crash, halt the core and let the model reason over the evidence:

  1. halt, then diagnose_fault — reads the Cortex-M SCB fault registers (CFSR/HFSR/MMFAR/BFAR/SHCSR/CPUID) plus PC/SP/LR in one call and returns a compact structured bundle with the set fault bits. It reports evidence; it does not assert a root cause.
  2. unwind_exception with elf_path — maps the crash to source lines. On the probe-rs backend this is a full DWARF backtrace (function + file:line per frame); on the OpenOCD backend it reads the exception stack frame and maps the faulting PC / caller LR.

Both are Cortex-M specific (SCB registers, ARM exception frame) and do not apply to Xtensa (ESP32) targets. The firmware must be built with debug info (.debug_line) for source mapping.

Safety Notes

  • Flash erase is disabled unless security.allow_flash_erase or flash.allow_erase is enabled.
  • Memory writes are controlled by security.allow_memory_write.
  • Optional memory range restriction uses target memory regions in the configuration.
  • Firmware file paths are canonicalized, checked against security.allowed_file_paths when configured, and checked against size limits.
  • Sector erase by arbitrary address is rejected until target-specific sector mapping is implemented.
  • flash_verify supports raw data comparison. Use raw BIN files or hex data for file-based verification.

Generate a starting configuration:

embedded-debugger-mcp config generate > embedded-debugger.toml
embedded-debugger-mcp --config embedded-debugger.toml config validate

STM32 Demo

The STM32 RTT demo is in examples/STM32_demo.

cd examples/STM32_demo
CARGO_TARGET_DIR=/tmp/embedded-debugger-mcp-stm32-target cargo +nightly check --locked

The demo firmware shows multi-channel RTT communication and is intended as a hardware validation aid. See examples/STM32_demo/README.md.

Release Checks

Run these before cutting a release:

cargo fmt --all -- --check
cargo clippy --locked --all-targets --all-features -- -D warnings
cargo test --locked --all-targets --all-features
RUSTDOCFLAGS="-D warnings" cargo doc --locked --all-features --no-deps
cargo package --locked
python3 .github/scripts/validate_skill.py skills/embedded-debugger
claude plugin validate .
embedded-debugger-mcp skill install --target both --home /tmp/embedded-debugger-skill-home --force --json
(cd examples/STM32_demo && CARGO_TARGET_DIR=/tmp/embedded-debugger-mcp-stm32-target cargo +nightly check --locked)

Acknowledgments

  • probe-rs for embedded debug probe support.
  • rmcp for the Rust MCP SDK.
  • tokio for the async runtime.

License

This project is licensed under the MIT License. See LICENSE.

Files in the repo

Repository payload13 top-level entries
  • .claude-plugin
  • .github
  • examples
  • skills
  • src
  • tests
  • .gitignore
  • Cargo.lock
  • Cargo.toml
  • CHANGELOG.md
  • LICENSE
  • README_zh.md
  • README.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k
t8y2/dbxConnectors

20 MB lightweight cross-platform database client for 90+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | 轻量级跨平台数据库管理工具,支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、达梦等 90+ 数据库,提供桌面端、Docker、CLI、内置 AI 助手和 MCP Server。

19k