AutoFixture MCP Server
A Model Context Protocol (MCP) server that provides comprehensive documentation and usage examples for the AutoFixture testing library.
README
AutoFixture MCP Server
A Model Context Protocol (MCP) server that provides comprehensive documentation and usage examples for the AutoFixture testing library. This server runs in a Docker container and can be easily integrated with VSCode, Cursor, or Claude Desktop.
Features
- Quick Start Guide: Get up and running with AutoFixture basics
- Method Search: Search for specific AutoFixture methods and their usage
- Class Information: Detailed documentation for core AutoFixture classes
- Package Information: NuGet package details for all AutoFixture extensions
- Usage Patterns: Common patterns and code examples
- Best Practices: Recommended approaches for using AutoFixture
- GitHub Documentation: Fetch latest docs directly from the repository
Available Tools
- get_quick_start: Get AutoFixture quick start guide and basic usage examples
- search_methods: Search for AutoFixture methods (e.g., 'Create', 'Build', 'Freeze')
- get_class_info: Get detailed information about classes like 'Fixture' or 'IFixture'
- get_packages: List AutoFixture NuGet packages by category (core/mocking/testing/all)
- get_usage_pattern: Get common usage patterns (e.g., 'customizing', 'automaq', 'xunit')
- get_best_practices: Get AutoFixture best practices and recommendations
- fetch_github_docs: Fetch latest documentation from GitHub (README, cheatsheet, FAQ)
Prerequisites
- Docker installed on your system
- Node.js 20+ (for local development)
- VSCode, Cursor, or Claude Desktop
Quick Setup
Option 1: Using Docker (Recommended)
-
Build the Docker image:
docker build -t autofixture-mcp-server:latest . -
Test the server:
docker run --rm -i autofixture-mcp-server:latest
Option 2: Using Docker Compose
docker-compose up -d
Integration with Cursor/VSCode
Cursor Setup
- Open Cursor settings (Cmd+Shift+P → "Preferences: Open User Settings (JSON)")
- Add the MCP server configuration:
{
"mcp": {
"servers": {
"autofixture": {
"command": "/Users/admin/dev/mcp/mcp-wrapper.sh"
}
}
}
}
Or use the provided config file:
# Copy the configuration
cat cursor-mcp-config.json
# Add to your Cursor settings
VSCode with Claude Code
-
Install the Claude Code extension
-
Open your MCP configuration file:
- On macOS:
~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json - On Linux:
~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json - On Windows:
%APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json
- On macOS:
-
Add the server configuration:
{
"mcpServers": {
"autofixture": {
"command": "/Users/admin/dev/mcp/mcp-wrapper.sh",
"args": [],
"env": {}
}
}
}
Claude Desktop Setup
-
Open Claude Desktop settings:
- On macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - On Windows:
%APPDATA%\Claude\claude_desktop_config.json - On Linux:
~/.config/Claude/claude_desktop_config.json
- On macOS:
-
Add the server configuration:
{
"mcpServers": {
"autofixture": {
"command": "/Users/admin/dev/mcp/mcp-wrapper.sh",
"args": [],
"env": {}
}
}
}
- Restart Claude Desktop
Local Development Setup
If you want to develop or modify the server locally:
-
Install dependencies:
npm install -
Build the project:
npm run build -
Run locally (without Docker):
npm start -
Development mode with auto-rebuild:
npm run dev
Usage Examples
Once integrated, you can use the MCP server in your conversations:
Example 1: Getting Started
User: "Use the autofixture MCP to show me how to get started with AutoFixture"
AI: [Calls get_quick_start tool and provides quick start guide]
Example 2: Searching for Methods
User: "Search for methods related to creating objects in AutoFixture"
AI: [Calls search_methods with query "create" and shows available methods]
Example 3: Getting Usage Patterns
User: "Show me how to use AutoFixture with xUnit"
AI: [Calls get_usage_pattern with pattern "xunit" and provides examples]
Example 4: Package Information
User: "What AutoFixture packages are available for mocking?"
AI: [Calls get_packages with category "mocking" and lists all mocking packages]
Configuration Files
mcp-config.json: Generic MCP configurationcursor-mcp-config.json: Cursor-specific configurationclaude_desktop_config.json: Claude Desktop configurationdocker-compose.yml: Docker Compose configurationmcp-wrapper.sh: Shell script wrapper for Docker integration
Troubleshooting
Server not starting
- Ensure Docker is running:
docker ps - Check Docker logs:
docker logs autofixture-mcp-server - Rebuild the image:
docker build -t autofixture-mcp-server:latest .
Permission issues with wrapper script
chmod +x mcp-wrapper.sh
Cursor/VSCode not detecting the server
- Restart the editor after adding configuration
- Check that the wrapper script path is absolute
- Verify Docker is installed:
docker --version
Testing the server manually
# Run the wrapper script directly
./mcp-wrapper.sh
# Or use Docker directly
docker run --rm -i autofixture-mcp-server:latest
Project Structure
.
├── src/
│ └── index.ts # Main MCP server implementation
├── dist/ # Compiled JavaScript (generated)
├── Dockerfile # Docker image configuration
├── docker-compose.yml # Docker Compose setup
├── mcp-wrapper.sh # Shell wrapper for Docker
├── package.json # Node.js dependencies
├── tsconfig.json # TypeScript configuration
├── mcp-config.json # Generic MCP config
├── cursor-mcp-config.json # Cursor-specific config
├── claude_desktop_config.json # Claude Desktop config
└── README.md # This file
Architecture
The server is built using:
- TypeScript: Type-safe server implementation
- @modelcontextprotocol/sdk: Official MCP SDK
- axios: HTTP client for fetching GitHub documentation
- cheerio: HTML parsing (for future enhancements)
- Docker: Containerization for easy deployment
Contributing
Feel free to extend the server with additional tools:
- Add new tool definitions in the
ListToolsRequestSchemahandler - Implement the tool logic in the
CallToolRequestSchemahandler - Rebuild the Docker image
License
MIT
Resources
- AutoFixture GitHub Repository
- AutoFixture Documentation
- Model Context Protocol Specification
- MCP SDK Documentation
Version
1.0.0
Built with MCP for enhanced AI-assisted development with AutoFixture.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。