MonoGame MCP Server
Provides AI-powered tools for MonoGame development, including API documentation lookup, project management, and code scaffolding. It enables users to create, build, and diagnose projects through integrated dotnet and content pipeline automation.
README
MonoGame MCP Server
A Model Context Protocol (MCP) server for the MonoGame framework. It provides AI-powered documentation lookup, project management, code scaffolding, and diagnostic tools for MonoGame development.
Quick Start
- Install prerequisites (.NET SDK 8.0 and MonoGame templates).
- Configure your MCP client (like Claude Desktop) to use
npx monogame-mcp. - Restart your client and start building MonoGame projects.
Prerequisites
- Node.js: version 18 or higher.
- .NET SDK 8.0: Required for building and running projects. Verify with
dotnet --version. - MonoGame Templates: Install with
dotnet new install MonoGame.Templates.CSharp. - MGCB Tool: Install for content builds with
dotnet tool install -g dotnet-mgcb.
Installation
Using npx (Recommended)
You can run the server directly without local installation:
npx monogame-mcp
Global Installation
npm install -g monogame-mcp
Docker
docker run -i monogame-mcp
Configuration
Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"monogame-mcp": {
"command": "npx",
"args": ["-y", "monogame-mcp"]
}
}
}
If using Docker:
{
"mcpServers": {
"monogame-mcp": {
"command": "docker",
"args": ["run", "-i", "monogame-mcp"]
}
}
}
Available Tools
| Tool Name | Description | Example Usage |
|---|---|---|
monogame_api_lookup |
Search MonoGame API documentation for classes, methods, and properties | { "query": "SpriteBatch" } |
monogame_create_project |
Create a new MonoGame project using dotnet templates | { "projectName": "MyGame", "template": "desktopgl" } |
monogame_manage_content |
Add, remove, or configure assets in a .mgcb content project | { "action": "add", "mgcbPath": "Content.mgcb", "assetPath": "player.png" } |
monogame_build_content |
Build MonoGame content using MGCB CLI | { "mgcbPath": "Content/Content.mgcb" } |
monogame_scaffold_code |
Generate MonoGame C# code from predefined templates | { "template": "game-class", "className": "MainGame" } |
monogame_diagnose_error |
Diagnose MonoGame error messages and suggest fixes | { "errorMessage": "Could not find ContentTypeReader" } |
monogame_build_run |
Build or run MonoGame projects using dotnet CLI | { "action": "run", "projectPath": "MyGame.csproj" } |
Available Resources
| URI Template | Description | Example URI |
|---|---|---|
monogame://api/{className} |
API reference documentation for MonoGame classes | monogame://api/Texture2D |
monogame://examples/{topic} |
Code examples and tutorials for development | monogame://examples/sprite-animation |
monogame://content-pipeline/{topic} |
Documentation for the Content Pipeline | monogame://content-pipeline/overview |
monogame://platforms/{platform} |
Platform-specific guides | monogame://platforms/android |
Available Prompts
| Prompt Name | Arguments | Description |
|---|---|---|
monogame_code_review |
code (required), focus |
Review C# code for MonoGame best practices |
monogame_troubleshoot |
error (required), code, platform |
Troubleshoot errors and exceptions |
monogame_architecture |
gameType (required), features, scale |
Plan game architecture and organization |
monogame_implement_feature |
feature (required), existingCode, platform |
Step-by-step feature implementation guidance |
Examples
1. Creating a New Project
Tell the AI: "Create a new MonoGame DesktopGL project named SpaceExplorer, add a background.png texture to content, and build it."
The AI will use monogame_create_project, then monogame_manage_content, and finally monogame_build_content.
2. Learning the API
Ask: "How do I use SpriteBatch to draw a scaled texture?"
The AI will use monogame_api_lookup or read monogame://api/SpriteBatch to provide exact parameters and code.
3. Fixing Errors
If you get an error: "ContentLoadException: The content file was not found."
Provide the error to the AI. It will use monogame_diagnose_error to identify that you likely missed adding the asset to your .mgcb file or have a path mismatch.
4. Scaffolding and Running
Ask: "Generate a scene manager class for my game and then try to run the project."
The AI will use monogame_scaffold_code with the scene-manager template, then monogame_build_run with the run action.
Development
- Clone the repository.
- Install dependencies:
npm install - Build the project:
npm run build - Run tests:
npm test - Link for local testing:
npm link
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.