diagnose_fault
Read 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.
How to use it
Project documentation lists diagnose_fault for the Embedded Debugger MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), then check which tools your installed version makes available. Tool availability can depend on configuration and credentials. A server handshake does not verify this tool’s behavior. See the full listing for setup details.
FULL EMBEDDED DEBUGGER MCP LISTINGOther tools in Embedded Debugger MCP (23)
Clear a hardware breakpoint.
Open a probe session for a target chip.
Drop the session and clean up resources.
Erase flash when erase permissions are enabled.
Program ELF, HEX, or BIN files through probe-rs flash algorithms.
Compare raw expected data with target flash contents.
Read core/session status.
Halt core execution.
Discover connected debug probes.
Show active session information.
Read target memory with configured size/range limits.
Reset the core. Only the implemented hardware-style reset path is accepted.
Attach to a SEGGER RTT control block.
List discovered RTT channels.
Detach RTT.
Read from an up channel with max byte and timeout limits.
Write to a down channel.
Resume execution.
Erase, program, reset/run, and optionally attach RTT.
Set a hardware breakpoint.
Single-step one instruction.
Unwind 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 li
Write target memory when enabled by configuration.