Yokai
Simple, modular, and observable Go framework for backend applications.
What is Yokai?
Yokai is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to simple, modular, and observable go framework for backend applications.
Simple, modular, and observable Go framework for backend applications.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Simple, modular, and observable Go framework for backend app
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx yokaiConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Yokai
Yokai is a simple, modular, and observable Go framework for building production-grade backend applications, including HTTP servers, gRPC services, MCP (Model Context Protocol) servers, and background workers. It eliminates boilerplate by providing dependency injection, Viper-based configuration management, built-in observability (tracing, metrics, logging), and a standardized project layout. Developers use it as the foundation when building Go-based MCP servers that need enterprise-grade infrastructure from the start.
Prerequisites
- Go 1.21 or later installed
- Basic familiarity with Go modules and dependency injection patterns
- An MCP-compatible client such as Claude Desktop or Cursor
- Docker (optional, for containerized deployment)
Create a new Go module
Initialize a new Go project that will use Yokai as its framework.
mkdir my-mcp-server && cd my-mcp-server
go mod init github.com/yourorg/my-mcp-serverAdd Yokai as a dependency
Add the core Yokai package to your Go module.
go get github.com/ankorstore/yokaiScaffold from an MCP template
Yokai provides ready-to-use application templates. Clone the MCP demo application from the Yokai showroom as a starting point for your MCP server.
git clone https://github.com/ankorstore/yokai-showroom.git
cd yokai-showroom/yokai-mcp-demoConfigure your application
Yokai uses Viper for configuration management. Edit the config/config.yaml file to set your application name, port, log level, and any service-specific settings. Environment variables can override any config value using the YOKAI_ prefix.
app:
name: my-mcp-server
env: development
debug: false
server:
port: 8080
log:
level: infoBuild and run the server
Compile and run your Yokai MCP server. It will start with the configured transport and begin accepting MCP client connections.
go run main.goConnect your MCP client
Add the running Yokai MCP server to your MCP client configuration to start using it.
Yokai Examples
Client configuration
Add a locally running Yokai MCP server to your Claude Desktop configuration.
{
"mcpServers": {
"yokai": {
"command": "npx",
"args": ["yokai"],
"env": {}
}
}
}Prompts to try
Example prompts once your Yokai-based MCP server exposes custom tools.
- "List all registered tools available on this server"
- "What HTTP endpoints does the application expose?"
- "Show me the current application health and observability metrics"
- "Execute the greet tool with name set to 'World'"Troubleshooting Yokai
Build fails with missing Yokai modules
Run 'go mod tidy' to resolve and download all transitive dependencies declared in your go.mod file.
Configuration values are not being applied
Check that your config/config.yaml file exists and is valid YAML. Yokai uses Viper, so environment variables with the YOKAI_ prefix will override file-based config values.
MCP client cannot connect to the server
Verify the server is listening on the expected port and that the transport type (stdio, SSE, or HTTP) in your Yokai config matches what your MCP client is configured to use.
Frequently Asked Questions about Yokai
What is Yokai?
Yokai is a Model Context Protocol (MCP) server that simple, modular, and observable go framework for backend applications. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Yokai?
Follow the installation instructions on the Yokai GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Yokai?
Yokai works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Yokai free to use?
Yes, Yokai is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Yokai Alternatives — Similar Developer Tools Servers
Looking for alternatives to Yokai? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Yokai in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Yokai?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.