MCP-Nexus
AI-powered Windows crash dump analysis platform that provides structured access to Microsoft debugging tools through the Model Context Protocol, making complex crash investigation accessible to AI systems
MCP Nexus
AI-Powered Windows Crash Dump Analysis Platform

MCP Nexus is a comprehensive Model Context Protocol (MCP) server that provides AI systems with advanced Windows crash dump analysis capabilities. It combines the power of Microsoft's debugging tools (WinDBG/CDB) with intelligent analysis workflows, making professional-grade crash investigation accessible to AI assistants.
๐ฏ What is MCP Nexus?
MCP Nexus is a platform that provides structured access to Windows debugging tools through the Model Context Protocol. It makes crash dump analysis more accessible by providing standardized tools and real-time progress tracking.
The Problem We Solve
Traditional Crash Analysis Challenges:
- ๐ Complexity: Requires deep knowledge of Windows internals and debugging tools
- โฑ๏ธ Time-consuming: Manual analysis can take hours or days
- ๐ง Expertise Required: Need specialized debugging skills and experience
- ๐ Inconsistent Results: Different analysts may reach different conclusions
- ๐ง Tool Complexity: WinDBG/CDB have steep learning curves
MCP Nexus Solution:
- ๐ง Structured Access: Provides standardized tools for debugging operations
- โก Real-time Updates: Live progress tracking and notifications
- ๐ Consistent Results: Provides structured output formats
- ๐ MCP Integration: Works with AI clients through Model Context Protocol
- ๐ ๏ธ Professional Tools: Built on Microsoft's industry-standard debugging infrastructure
โจ Key Features
- ๐ Advanced Crash Analysis: Leverage WinDBG/CDB for comprehensive dump analysis
- ๐ค AI-Native Design: Built specifically for AI agent integration via MCP
- โก Command Batching: Intelligent command grouping for improved throughput
- ๐ Real-time Notifications: Live updates during analysis operations
- ๐ก๏ธ Session Management: Robust session lifecycle with automatic cleanup
- ๐ฏ Extensible Architecture: PowerShell-based extension system for custom workflows
- ๐ Structured Results: Parse debugging output into AI-friendly formats
๐ฏ Quick Start
Prerequisites
- .NET 8.0 Runtime or SDK
- Windows Debugging Tools (WinDBG/CDB) - Download from Microsoft
Installation
# Clone the repository
git clone https://github.com/CapulusCodeNinja/mcp_nexus.git
cd mcp_nexus
# Build the project
dotnet build
# Run the server
dotnet run --project nexus/nexus.csproj
๐ค AI Integration
In this chapter, we provide example configurations for integrating MCP Nexus with popular AI development environments using both STDIO and HTTP protocols. In similar fashion, you can adapt these configurations for other MCP-compatible clients.
Cursor IDE Integration
STDIO Integration

{
"mcpServers": {
"mcp_nexus": {
"type": "stdio",
"command": "dotnet",
"args": [
"run",
"--project",
"C:\\Sources\\Github\\CapulusCodeNinja\\mcp_nexus\\nexus\\nexus.csproj",
"--",
"--stdio"
]
}
}
}
HTTP Integration

{
"mcpServers": {
"mcp-nexus": {
"url": "http://0.0.0.0:5511/",
"headers": {
"Content-Type": "application/json"
}
}
}
}
Google Antigravity Integration
STDIO Integration

{
"mcpServers": {
"mcp_nexus": {
"command": "C:\\Program Files\\dotnet\\dotnet.exe",
"args": [
"run",
"--project",
"C:\\Sources\\Github\\CapulusCodeNinja\\mcp_nexus\\nexus\\nexus.csproj",
"--",
"--stdio"
]
}
},
"inputs": []
}
HTTP Integration

{
"mcpServers": {
"mcp-nexus": {
"serverUrl": "http://0.0.0.0:5511/",
"headers": {
"Content-Type": "application/json"
}
}
}
}
Visual Studio Code Integration
STDIO Integration

{
"servers": {
"mcp_nexus": {
"type": "stdio",
"command": "dotnet",
"args": [
"run",
"--project",
"C:\\Sources\\Github\\CapulusCodeNinja\\mcp_nexus\\nexus\\nexus.csproj",
"--",
"--stdio"
]
}
}
}
HTTP Integration

{
"servers": {
"mcp-nexus": {
"url": "http://0.0.0.0:5511/",
"headers": {
"Content-Type": "application/json"
}
}
}
}
๐ ๏ธ Available MCP Tools
Core Analysis Tools
nexus_open_dump_analyze_session- Open a crash dump for analysisnexus_enqueue_async_dump_analyze_command- Execute WinDBG commands asynchronouslynexus_get_dump_analyze_commands_status- Get status of all commands (bulk polling)nexus_read_dump_analyze_command_result- Read individual command resultsnexus_cancel_dump_analyze_command- Cancel a running commandnexus_close_dump_analyze_session- Close session and cleanup resources
MCP Resources
sessions- List all active debugging sessionscommands- List commands with filtering by session/stateextensions- List available PowerShell extension scriptsusage- Complete usage guide with exampleshealth- System health and metrics
๐ Example Workflow
Typical AI-driven crash analysis workflow:
- Open Session:
nexus_open_dump_analyze_sessionwith dump file path - Queue Commands: Use
nexus_enqueue_async_dump_analyze_commandfor:!analyze -v(automatic crash analysis)kL(stack trace with source lines)!threads(thread information)
- Monitor Progress:
nexus_get_dump_analyze_commands_status(bulk polling) - Retrieve Results:
nexus_read_dump_analyze_command_resultfor each command - Close Session:
nexus_close_dump_analyze_sessionfor cleanup
Example conversation with AI assistant:
User: "Analyze the crash dump at C:\dumps\myapp.dmp"
AI: I'll analyze that crash dump for you.
[Opens session, queues !analyze -v, kL, !threads commands]
Analysis Results:
- Exception: Access Violation (0xC0000005)
- Faulting Module: myapp.exe
- Root Cause: Null pointer dereference in ProcessData()
- Stack shows: ProcessData+0x42 called with null buffer
Recommendation: Add null check before buffer access.
๐๏ธ Architecture
Modular Structure
nexus/ - Main application (entry point, hosting)
nexus_config/ - Configuration and logging
nexus_engine/ - Debug engine (CDB sessions, command queue)
nexus_engine_batch/ - Command batching system
nexus_protocol/ - MCP protocol layer (tools, resources)
nexus_setup/ - Service installation and management
nexus_external_apis/ - Shared utilities (file system, process, etc.)
nexus_extensions/ - PowerShell extension system
Key Design Patterns
- Modular Architecture: Clear separation of concerns across libraries
- Singleton Pattern: Core engine accessible without DI overhead
- Command Queue: Asynchronous command processing with state management
- Batching: Transparent command grouping for improved performance
- Event-Driven: Real-time notifications for command state changes
๐งช Testing & Quality
Test Statistics
- โ 1247 total tests (all passing)
- ๐ 87.1% line coverage (target: 75%)
- ๐ 77.8% branch coverage (target: 75%)
- โก Fast execution (~12 seconds for full suite)
- ๐ฏ Zero build warnings
โ๏ธ Configuration
Command Batching
MCP Nexus intelligently batches commands for improved throughput:
{
"McpNexus": {
"DebugEngine": {
"Batching": {
"Enabled": true,
"MinBatchSize": 2,
"MaxBatchSize": 5,
"ExcludedCommands": [
"!analyze", "!dump", "!heap", "!memusage"
]
}
}
}
}
Session Management
{
"McpNexus": {
"SessionManagement": {
"MaxConcurrentSessions": 10,
"SessionTimeoutMinutes": 30,
"CleanupIntervalSeconds": 300,
"DefaultCommandTimeoutMinutes": 10,
"DeleteDumpFileOnSessionClose": false
}
}
}
Logging
{
"Logging": {
"LogLevel": "Information"
}
}
Supported levels: Trace, Debug, Information, Warning, Error, Critical
๐ Advanced Features
Extension System
Create custom analysis workflows with PowerShell:
# extensions/my-analysis/my-analysis.ps1
Import-Module McpNexusExtensions
$result1 = Invoke-NexusCommand -Command "!analyze -v"
$result2 = Invoke-NexusCommand -Command "kL"
# Process results and return structured data
return @{
CrashType = "Access Violation"
RootCause = "Null pointer dereference"
Recommendations = @("Add null checks", "Review error handling")
}
Real-time Notifications
Receive live updates during analysis:
{
"jsonrpc": "2.0",
"method": "notifications/commandStatus",
"params": {
"commandId": "cmd-abc123",
"sessionId": "session-xyz789",
"state": "Executing",
"timestamp": "2025-01-15T10:30:00Z"
}
}
๐ก๏ธ Service Mode
Run as a Windows Service for production environments:
# Install as service
dotnet run --project nexus/nexus.csproj -- service install
# Start service
net start MCP-Nexus
# Stop service
net stop MCP-Nexus
# Uninstall service
dotnet run --project nexus/nexus.csproj -- service uninstall
๐ License
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
The Apache License 2.0 allows you to:
- โ Use the software commercially
- โ Modify and distribute
- โ Sublicense
- โ Use patent claims
- โ ๏ธ Include copyright notice
๐ Acknowledgments
- Model Context Protocol - MCP specification
- C# SDK for MCP - MCP implementation
- Microsoft Debugging Tools - WinDBG/CDB
- NLog - Logging framework
Related Servers
Scout Monitoring MCP
sponsorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
MCP Chart Server
Generates TradingView chart visualizations using the Chart-IMG API.
MCP Inspector
A developer tool for testing and debugging MCP servers with a web-based UI.
Remote MCP Server on Cloudflare (Authless)
An example of a remote MCP server without authentication, deployable on Cloudflare Workers.
mcp-ssh-sre
An MCP server providing read-only server monitoring tools to AI assistants. Runs predefined diagnostic commands over SSH and passes only the results to the LLM - your server credentials and shell are never exposed.
Read Docs MCP
Enables AI agents to access and understand package documentation from local or remote repositories.
Remote MCP Server (Authless)
An example of a remote MCP server deployable on Cloudflare Workers, without authentication.
GPT Image 1
Generate high-quality AI images with OpenAI's GPT-Image-1 model and save them directly to your local machine.
Volatility3 MCP Server
Perform advanced memory forensics analysis using Volatility3 via a conversational interface. Requires user-specified memory dump files.
Simple MCP Server
A starter MCP server built with TypeScript and the official MCP SDK, featuring example tools like echo, add, time, and flight status.
Google Tag Manager
Integrates Google Tag Manager to automate GTM configuration and component creation through natural language prompts.