crash-mcp
Click on "Deploy 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., "@crash-mcp load tests/core and show me why it crashed"
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.
crash-mcp
crash-mcp is an MCP server that inspects native crash dumps (ELF core and Windows minidump) and presents the crash reason, faulting thread, and stack trace to an AI assistant. It never executes the dump.
Turkish / Türkçe: crash-mcp, ELF core ve Windows minidump çökme dökümlerini inceleyen bir MCP sunucusudur. Çökme nedeni, hata veren iş parçacığı ve stack trace'i bir AI asistanına sunar. Döküm dosyasını asla çalıştırmadan, salt okunur analiz yapar.
Platform Support
Platform | ELF core (gdb) | Windows minidump | Notes |
Linux | ✅ Full | ✅ Yes | gdb required for ELF core stack traces |
Windows | ⚠️ Summary only | ✅ Full | gdb is not available; minidump is the primary path |
macOS | ⚠️ Summary only | ✅ Yes | gdb may not be installed |
On Windows, ELF core dumps can still be parsed for basic info (arch, threads,
modules), but stack traces via gdb are unavailable. Windows minidump files
are fully supported.
Related MCP server: MCP Server for WinDbg Crash Analysis
Install
From PyPI (when published)
pip install crash-mcpFrom GitHub
pip install git+https://github.com/RivaExits0/crash-mcp.gitFrom Source
git clone https://github.com/RivaExits0/crash-mcp.git
cd crash-mcp
pip install -e .[dev] # or just `pip install -e .` for productionSystem requirements (Linux):
gcc,gdb, andbinutilsfor building test fixture. Optional: installgdbfor ELF core stack traces (Linux only).
Build the Test Fixture (Linux)
makeCompiles tests/crash and generates tests/core. Requires gcc and a kernel
that allows core dumps. On Windows, skip this step; minidump tests use mocks.
Run
crash-mcp
# or
python -m crash_mcpThe server speaks MCP over stdio.
Claude Desktop Integration
Add to claude_desktop_config.json:
{
"mcpServers": {
"crash-mcp": {
"command": "crash-mcp",
"args": [],
"env": {}
}
}
}Windows: If installed via pip,
crash-mcpshould be on PATH. Otherwise use full path:C:\\path\\to\\crash-mcp\\.venv\\Scripts\\crash-mcp.exe.
OpenCode Integration
Add to opencode.json:
{
"mcp": {
"crash": {
"type": "local",
"command": ["crash-mcp"],
"enabled": true
}
}
}MCP Tools
Tool | Description | When to call |
| Load a dump (ELF core or Windows minidump) and detect its format. | First, before any other crash_* tool. |
| Crash type, faulting address, thread, arch, module, symbols. | After |
| List threads (paginated). | To find the faulting thread. |
| Stack frames for a thread. | After |
| Disassemble around an address. | To inspect instructions near crash PC. |
| Compare two dumps. | To check if two crashes are similar. |
Tool: crash_load
Example call:
{"tool": "crash_load", "args": {"dump_path": "tests/core", "binary_paths": ["tests/crash"]}}Example output:
{
"format": "ELF core",
"arch": "arm64",
"os": "Linux/Unix",
"process_name": "crash",
"crash_thread": 4486,
"crash_signal": "SIGSEGV",
"signal_code": 1,
"crash_pc": "0x4007c4",
"crash_pc_str": "0x4007c4 (/path/to/tests/crash+0x7c4)",
"thread_count": 1,
"module_count": 3,
"gdb_available": true
}Tool: crash_summary
Example call:
{"tool": "crash_summary", "args": {}}Example output:
{
"format": "ELF core",
"arch": "arm64",
"crash_signal": "SIGSEGV",
"crash_thread": 4486,
"crash_pc": "0x4007c4",
"process_name": "crash"
}Tool: crash_threads
Example call:
{"tool": "crash_threads", "args": {"limit": 5, "offset": 0}}Example output:
{
"total": 1,
"offset": 0,
"limit": 5,
"threads": [
{
"thread_id": 4486,
"state": "crashed",
"signal": 11,
"pc": "0x4007c4",
"pc_str": "0x4007c4 (/path/to/tests/crash+0x7c4)"
}
]
}Tool: crash_stack
Example call:
{"tool": "crash_stack", "args": {"thread_id": 4486, "limit": 10, "offset": 0}}Example output:
{
"thread_id": 4486,
"source": "gdb",
"total": 2,
"offset": 0,
"limit": 10,
"frames": [
{"index": 0, "text": "#0 0x00000000004007c4 in boom (x=42) at crash.c:6"},
{"index": 1, "text": "#1 0x00000000004007e4 in main () at crash.c:10"}
],
"gdb_error": null
}Tool: crash_disassemble
Example call:
{"tool": "crash_disassemble", "args": {"address": "0x4007c4", "before": 2, "after": 2}}Example output:
{
"address": "0x4007c4",
"address_str": "0x4007c4 (/path/to/tests/crash+0x7c4)",
"before": 2,
"after": 2,
"instructions": [
{"address": 0x4007c0, "mnemonic": "str", "op_str": "w1, [x8]", "bytes": "..."},
{"address": 0x4007c4, "mnemonic": "ret", "op_str": "", "bytes": "..."}
]
}Tool: crash_compare
Example call:
{"tool": "crash_compare", "args": {"dump_path_a": "tests/core", "dump_path_b": "tests/core"}}Example output:
{
"format_a": "elf_core",
"format_b": "elf_core",
"crash_signal_a": "SIGSEGV",
"crash_signal_b": "SIGSEGV",
"crash_pc_a": "0x4007c4",
"crash_pc_b": "0x4007c4",
"thread_count_a": 1,
"thread_count_b": 1
}Pagination (limit / offset)
crash_threads and crash_stack support limit and offset:
limit: maximum number of items to return (default 20 for threads, 30 for stack)offset: number of items to skip (default 0)
Response includes a pagination-style object with total, offset, limit, returned, and has_more.
Testing
Linux (full suite)
make testRuns the full pytest suite: ELF core integration (real core dump + gdb), minidump parser, MCP smoke test, error paths, pagination. 31 tests.
Windows (minidump only)
python -m pytest tests/test_minidump_mock.py tests/test_extra.py -qRuns minidump mock tests and session/validation tests that do not require a core dump or gdb.
macOS (minidump only)
python -m pytest tests/test_minidump_mock.py tests/test_extra.py -qArchitecture
src/crash_mcp/
├── server.py MCP tool definitions (stdio transport)
├── analyzer.py Session management and common reporting
├── elf_core.py ELF core parsing and gdb-based stack traces (Linux)
├── minidump_reader.py Windows minidump parsing
└── platform_utils.py Cross-platform paths, subprocess, file I/OSecurity
No
shell=True; external commands use argument lists with timeouts.No dump execution, no network, no filesystem scanning beyond provided paths.
Sensitive memory is not returned by default; only registers, addresses, frames.
Limitations
ELF core stack traces require gdb (Linux only).
Minidump stack traces are best-effort frame-pointer walks.
Minidump thread context parsing depends on the minidump library version.
On Windows, ELF core stack traces are unavailable (no gdb).
Static analysis cannot guarantee runtime behaviour.
🔗 Related Projects
forge-mcp — Game modding toolkit (hex, PE, APK, Unity, Unreal, tables). Use for hex editing, signature generation, APK repacking.
emu-mcp — Isolated function emulation with Unicorn. Use for verifying function behavior with concrete inputs.
henry-mcp — Static compatibility analysis for EXE/DLL/APK/Kotlin. Use for checking module compatibility.
📦 Release
Latest: v0.1.0
Install from release:
pip install git+https://github.com/RivaExits0/crash-mcp.git@v0.1.0
Create Release
git tag -a v0.1.0 -m "crash-mcp v0.1.0: Initial release"
git push origin v0.1.0License
MIT — see LICENSE.
Available Tools
6 toolscrash_compareB
Compare two crash dumps.
Use to check whether two crashes have the same type/address/module/thread counts. Best-effort; missing symbols are reported.
Inputs: dump_path_a (required), dump_path_b (required). Returns: result
crash_disassembleA
Disassemble memory around an address in the dump.
Use to inspect instructions near the crash address. before/after are instruction counts (capped). Returns an error if memory is unavailable.
Inputs: address (required), after, before. Returns: result
crash_loadA
Load a crash dump (ELF core or Windows minidump) into the session.
Use first, before any other crash_* tool. Detects format, architecture, threads, modules and exception info. Does not execute the dump. Missing binaries/symbols are reported, not guessed.
Inputs: dump_path (required), binary_paths, symbols_path. Returns: result
crash_stackA
Return stack frames for a thread.
Use after crash_threads to inspect a specific thread. Shows symbols when available, otherwise module+RVA. Paginated by limit/offset. Reports the reason if unwinding is unavailable.
Inputs: thread_id (required), limit, offset. Returns: result
crash_summaryA
Return a short summary of the loaded dump.
Use to get crash type, faulting address, faulting thread, arch, module and symbol resolution status. Returns unknown for missing fields.
Inputs: no named parameters. Returns: result
crash_threadsA
List threads in the loaded dump.
Use to find the faulting thread or inspect thread states. Supports limit/offset pagination.
Inputs: limit, offset. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool maps to a distinct action in a clear pipeline: load the dump, summarize it, enumerate threads, unwind a stack, disassemble at an address, and compare two dumps. Descriptions explicitly sequence the tools (load first, stack after threads), so there is no realistic misselection between them.
All six tools use the same crash_ prefix followed by a short lowercase noun/verb token (load, summary, threads, stack, disassemble, compare). The pattern is uniform and predictable, making the set easy to scan.
Six tools is a tight, well-scoped surface for crash dump triage; every tool has a distinct job and none appear redundant. Nothing feels padded or arbitrarily split.
The core workflow (load → summary → threads → stack → disassemble → compare) is fully covered, including pagination and graceful error reporting. However, there is no register inspection, module listing, or memory/string search tool, which are common needs in crash analysis and would force workarounds.
Maintenance
Related MCP Connectors
Hunt zero-days by talking to binaries. 40+ tools. Hosted, OAuth + SSO, invite: hi@byteray.ai
Shared debugging memory for AI coding agents
Real-time CVE, exploit, and vulnerability intelligence for AI assistants (350K+ CVEs, 115K+ PoCs)
Code intelligence for LLMs. Analyze, search, and retrieve code from any public git repository.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables AI assistants to analyze Linux system crash dumps by automatically discovering dump files, matching kernels, and executing interactive crash analysis commands through the MCP protocol.67MIT
- AlicenseNot gradedqualityNot gradedmaintenanceBridges AI models with WinDbg to analyze Windows crash dumps and perform remote debugging through natural language queries, enabling execution of debugger commands and automated crash analysis.MIT
- AlicenseNot gradedqualityDmaintenanceAnalyzes application crash dumps and extracts debug symbols, transforming Windows minidump files into readable stack traces and providing AI-powered crash analysis to help identify root causes and fix critical issues.8MIT
- AlicenseNot gradedqualityAmaintenanceBridges AI models with WinDbg for crash dump analysis and remote debugging.435 PyPI1,669MIT