Microsoft has introduced the Microsoft Binlog MCP Server, a new Model Context Protocol (MCP) server that gives AI assistants like GitHub Copilot direct access to MSBuild .binlog files. The server enables AI-powered build diagnosis, property tracing, performance analysis, and build comparison using natural language queries.
The tool was released in preview on June 17 and parses .binlog files to expose 15 specialized tools for AI-driven investigation. Microsoft says AI assistants can now:
- Investigate build failures by querying errors, warnings, and full project/target/task context
- Trace property origins to understand where a value came from
- Analyze performance bottlenecks by identifying the slowest projects, targets, and tasks
- Compare two builds to see how packages and properties changed
- Read embedded source files captured during the build
Instead of manually scrolling through the MSBuild Structured Log Viewer, developers can now ask their AI assistant questions like:
- “Why did my build fail?”
- “What’s making my build slow?”
MSBuild’s binary logs contain detailed information about every property evaluation, target execution, task invocation, error, and warning. Navigating that data manually can be overwhelming, especially in complex multi-project solutions. Using an AI coding assistant to handle these investigations can save significant time and effort.
How to Get Started
The easiest way to start using the Microsoft Binlog MCP Server is through the .NET Agent Skills repository. The dotnet-msbuild plugin, available for Visual Studio, Visual Studio Code, and terminal-based AI assistants like GitHub Copilot CLI and Claude Code, bundles the Microsoft Binlog MCP Server along with curated skills and agents for MSBuild build investigation and optimization.
