Allows building Unreal Engine projects by using MSBuild to compile Unreal Engine solutions and projects with specified configurations and platforms.
Click on "Install 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., "@msbuild-mcp-server Build C:\MyProject\MyApp.sln with Release|x64"
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.
A lightweight MCP (Model Context Protocol) server for automating MSBuild projects and solutions builds. It dynamically locates MSBuild and provides customizable build configuration options.
Dynamic MSBuild Discovery: Automatically detects the MSBuild executable, ensuring compatibility with various Visual Studio installations.
Customizable Build Settings: Easily configure build options such as configuration, platform, verbosity level, parallel build CPU count, NuGet restore, and additional command-line arguments through LLM-driven tool invocation.
Clear Error Reporting: Filters and presents concise, relevant error messages upon build failures.
MCP Client Compatibility: Supports seamless integration with popular MCP clients such as VSCode, Cursor, Windsurf, and more. Configuration snippets for these clients are provided in the documentation.
Cross-Language Support: Supports MSBuild-compatible projects, including .sln, .csproj, and .vcxproj files, enabling builds for languages like C#, C++, and more across Windows platforms.
Related MCP server: XcodeMCP
Ensure the following prerequisites are installed:
Python 3.11 or higher
Visual Studio or Visual Studio Build Tools (for MSBuild)
uv (recommended)
Ensure uv is installed.
In the MCP settings of your AI tools (e.g., Cursor, Windsurf, Claude Desktop, etc.), add the following configuration:
{
"mcpServers": {
"msbuild-mcp-server": {
"command": "uvx",
"args": [
"msbuild-mcp-server@latest"
]
}
}
}Place this snippet in your client configuration file:
VSCode: .vscode/mcp.json
Cursor: ~/.cursor/mcp.json or <project-root>/.cursor/mcp.json
Windsurf: ~/.codeium/windsurf/mcp_config.json
Restart your tool to ensure that the msbuild-mcp-server and its provided tools are properly registered.
AI agents can trigger builds using natural language like:
Basic Project Build
"Build this solution at
C:/Path/To/Project.slnusingRelease|x64."
Unreal Engine Build
"Build the solution located at
C:/Projects/MyGame/MyGame.slnusingDevelopment Editor|Win64."
This project is licensed under the MIT License.
Build an MSBuild project or solution (.sln, .csproj, .vcxproj) file using MSBuild.
This tool dynamically locates the MSBuild executable using the vswhere Python package. It supports flexible build configurations, including verbosity, platform, and additional arguments.
Parameters:
project_path: Path to the project or solution file to build.
configuration: Build configuration (e.g., Debug, Release).
platform: Target platform (e.g., x86, x64).
verbosity: MSBuild output verbosity (quiet, minimal, normal, detailed, diagnostic).
max_cpu_count: Maximum number of CPUs for parallel build (None for default).
restore: Whether to perform NuGet restore before build.
additional_args: Additional MSBuild command-line arguments.
Returns:
A string indicating the build result, including success or filtered error messages.
Use this tool to automate the build process for MSBuild projects, ensuring compatibility with various configurations and environments.
| Name | Required | Description | Default |
|---|---|---|---|
| project_path | Yes | ||
| configuration | No | Debug | |
| platform | No | x64 | |
| verbosity | No | minimal | |
| max_cpu_count | No | ||
| restore | No | ||
| additional_args | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses a key behavioral trait: dynamic location of MSBuild via vswhere. It also mentions return format (success or filtered error messages). However, it does not cover failure modes (e.g., when MSBuild not found), side effects, or authentication needs. With no annotations, more detail would improve transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is structured into sections (parameters, returns) which is helpful, but it is somewhat verbose. The opening sentence repeats the tool's action ('Build ... using MSBuild'). It could be tightened to front-load critical info without extra words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers tool purpose, parameters, and return format. However, it lacks context about error handling, environment dependencies (vswhere requirement), and when the tool might fail. Given no annotations and no output schema details, completeness is adequate but not thorough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the parameter list in the description provides essential meaning beyond the bare JSON schema. It explains each parameter's purpose (e.g., verbosity values, function of additional_args). However, it could be more precise about valid values for configuration and platform, and the default behaviors.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool builds MSBuild projects/solutions and lists supported file types (.sln, .csproj, .vcxproj). The verb 'build' is specific and the resource is well-defined, leaving no ambiguity about the tool's purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides basic usage guidance ('Use this tool to automate the build process') but lacks explicit when-to-use or when-not-to-use conditions. There are no sibling tools, so no need for differentiation, but it does not mention prerequisites or limitations like installation of vswhere.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Only one tool exists, so there is no ambiguity between tools.
The single tool name 'build_msbuild_project' follows a clear verb_noun pattern and is descriptive.
A single tool for building MSBuild projects is slightly under-scoped but reasonable for a focused server; additional tools like clean or list properties could be added.
The tool covers the core build operation with good configuration options, but lacks related operations such as clean or property listing, which may cause dead ends for some workflows.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Discover software problems, analyze evidence, and create implementation-ready Build plans.
The MCP server for Azure DevOps, bringing the power of Azure DevOps directly to your agents.
Build, deploy, and operate hosted web apps on VibeKit (vibekit.bot) from any MCP client.
Structured knowledge base for AI agent solutions. Search, explore, and retrieve build logs.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/zenoengine/msbuild-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
