go-mcp-server-generator
作者: github
生成生产就绪的Go MCP服务器项目,包含正确的结构、依赖关系和类型化工具实现。搭建完整的Go模块布局,集成官方MCP SDK,包括主服务器设置、工具注册和优雅关闭处理。提供类型化工具处理器,支持JSON模式验证、结构化输入/输出以及上下文感知的错误处理。包含通过环境变量进行配置管理、基础测试结构和README文档...
npx skills add https://github.com/github/awesome-copilot --skill go-mcp-server-generatorGo MCP Server Project Generator
Generate a complete, production-ready Model Context Protocol (MCP) server project in Go.
Project Requirements
You will create a Go MCP server with:
- Project Structure: Proper Go module layout
- Dependencies: Official MCP SDK and necessary packages
- Server Setup: Configured MCP server with transports
- Tools: At least 2-3 useful tools with typed inputs/outputs
- Error Handling: Proper error handling and context usage
- Documentation: README with setup and usage instructions
- Testing: Basic test structure
Template Structure
myserver/
├── go.mod
├── go.sum
├── main.go
├── tools/
│ ├── tool1.go
│ └── tool2.go
├── resources/
│ └── resource1.go
├── config/
│ └── config.go
├── README.md
└── main_test.go
go.mod Template
module github.com/yourusername/{{PROJECT_NAME}}
go 1.23
require (
github.com/modelcontextprotocol/go-sdk v1.0.0
)
main.go Template
package main
import (
"context"
"log"
"os"
"os/signal"
"syscall"
"github.com/modelcontextprotocol/go-sdk/mcp"
"github.com/yourusername/{{PROJECT_NAME}}/config"
"github.com/yourusername/{{PROJECT_NAME}}/tools"
)
func main() {
cfg := config.Load()
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
// Handle graceful shutdown
sigCh := make(chan os.Signal, 1)
signal.Notify(sigCh, os.Interrupt, syscall.SIGTERM)
go func() {
<-sigCh
log.Println("Shutting down...")
cancel()
}()
// Create server
server := mcp.NewServer(
&mcp.Implementation{
Name: cfg.ServerName,
Version: cfg.Version,
},
&mcp.Options{
Capabilities: &mcp.ServerCapabilities{
Tools: &mcp.ToolsCapability{},
Resources: &mcp.ResourcesCapability{},
Prompts: &mcp.PromptsCapability{},
},
},
)
// Register tools
tools.RegisterTools(server)
// Run server
transport := &mcp.StdioTransport{}
if err := server.Run(ctx, transport); err != nil {
log.Fatalf("Server error: %v", err)
}
}
tools/tool1.go Template
package tools
import (
"context"
"fmt"
"github.com/modelcontextprotocol/go-sdk/mcp"
)
type Tool1Input struct {
Param1 string `json:"param1" jsonschema:"required,description=First parameter"`
Param2 int `json:"param2,omitempty" jsonschema:"description=Optional second parameter"`
}
type Tool1Output struct {
Result string `json:"result" jsonschema:"description=The result of the operation"`
Status string `json:"status" jsonschema:"description=Operation status"`
}
func Tool1Handler(ctx context.Context, req *mcp.CallToolRequest, input Tool1Input) (
*mcp.CallToolResult,
Tool1Output,
error,
) {
// Validate input
if input.Param1 == "" {
return nil, Tool1Output{}, fmt.Errorf("param1 is required")
}
// Check context
if ctx.Err() != nil {
return nil, Tool1Output{}, ctx.Err()
}
// Perform operation
result := fmt.Sprintf("Processed: %s", input.Param1)
return nil, Tool1Output{
Result: result,
Status: "success",
}, nil
}
func RegisterTool1(server *mcp.Server) {
mcp.AddTool(server,
&mcp.Tool{
Name: "tool1",
Description: "Description of what tool1 does",
},
Tool1Handler,
)
}
tools/registry.go Template
package tools
import "github.com/modelcontextprotocol/go-sdk/mcp"
func RegisterTools(server *mcp.Server) {
RegisterTool1(server)
RegisterTool2(server)
// Register additional tools here
}
config/config.go Template
package config
import "os"
type Config struct {
ServerName string
Version string
LogLevel string
}
func Load() *Config {
return &Config{
ServerName: getEnv("SERVER_NAME", "{{PROJECT_NAME}}"),
Version: getEnv("VERSION", "v1.0.0"),
LogLevel: getEnv("LOG_LEVEL", "info"),
}
}
func getEnv(key, defaultValue string) string {
if value := os.Getenv(key); value != "" {
return value
}
return defaultValue
}
main_test.go Template
package main
import (
"context"
"testing"
"github.com/yourusername/{{PROJECT_NAME}}/tools"
)
func TestTool1Handler(t *testing.T) {
ctx := context.Background()
input := tools.Tool1Input{
Param1: "test",
Param2: 42,
}
result, output, err := tools.Tool1Handler(ctx, nil, input)
if err != nil {
t.Fatalf("Tool1Handler failed: %v", err)
}
if output.Status != "success" {
t.Errorf("Expected status 'success', got '%s'", output.Status)
}
if result != nil {
t.Error("Expected result to be nil")
}
}
README.md Template
# {{PROJECT_NAME}}
A Model Context Protocol (MCP) server built with Go.
## Description
{{PROJECT_DESCRIPTION}}
## Installation
\`\`\`bash
go mod download
go build -o {{PROJECT_NAME}}
\`\`\`
## Usage
Run the server with stdio transport:
\`\`\`bash
./{{PROJECT_NAME}}
\`\`\`
## Configuration
Configure via environment variables:
- `SERVER_NAME`: Server name (default: "{{PROJECT_NAME}}")
- `VERSION`: Server version (default: "v1.0.0")
- `LOG_LEVEL`: Logging level (default: "info")
## Available Tools
### tool1
{{TOOL1_DESCRIPTION}}
**Input:**
- `param1` (string, required): First parameter
- `param2` (int, optional): Second parameter
**Output:**
- `result` (string): Operation result
- `status` (string): Status of the operation
## Development
Run tests:
\`\`\`bash
go test ./...
\`\`\`
Build:
\`\`\`bash
go build -o {{PROJECT_NAME}}
\`\`\`
## License
MIT
Generation Instructions
When generating a Go MCP server:
- Initialize Module: Create
go.modwith proper module path - Structure: Follow the template directory structure
- Type Safety: Use structs with JSON schema tags for all inputs/outputs
- Error Handling: Validate inputs, check context, wrap errors
- Documentation: Add clear descriptions and examples
- Testing: Include at least one test per tool
- Configuration: Use environment variables for config
- Logging: Use structured logging (log/slog)
- Graceful Shutdown: Handle signals properly
- Transport: Default to stdio, document alternatives
Best Practices
- Keep tools focused and single-purpose
- Use descriptive names for types and functions
- Include JSON schema documentation in struct tags
- Always respect context cancellation
- Return descriptive errors
- Keep main.go minimal, logic in packages
- Write tests for tool handlers
- Document all exported functions
来自 github 的更多技能
console-rendering
github
在Go中使用基于结构体标签的控制台渲染系统的说明
official
acquire-codebase-knowledge
github
当用户明确要求映射、记录或熟悉现有代码库时使用此技能。触发词如“映射此代码库”、“记录…
official
acreadiness-assess
github
Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc…
official
acreadiness-generate-instructions
github
通过AgentRC指令命令生成定制化的AI代理指令文件。生成.github/copilot-instructions.md(默认,推荐用于VS Code中的Copilot…
official
acreadiness-policy
github
帮助用户选择、编写或应用AgentRC策略。策略通过禁用无关检查、覆盖影响/级别、设置…来定制就绪评分。
official
add-educational-comments
github
为代码文件添加教育性注释,将其转化为有效的学习资源。根据三个可配置的知识水平(初级、中级、高级)调整解释深度和语气。若未提供文件,自动请求文件,并附带编号列表以便快速选择。仅通过教育性注释将文件扩展最多125%(硬性限制:新增400行;超过1000行的文件限制为300行)。保留文件编码、缩进风格、语法正确性以及...
official
adobe-illustrator-scripting
github
使用ExtendScript(JavaScript/JSX)编写、调试和优化Adobe Illustrator自动化脚本。在创建或修改操作…的脚本时使用。
official
agent-governance
github
声明式策略、意图分类及审计追踪,用于控制AI代理工具访问与行为。可组合的治理策略定义允许/禁止的工具、内容过滤器、速率限制及审批要求——以配置而非代码形式存储。语义意图分类在执行工具前通过基于模式的信号检测危险提示(数据泄露、权限提升、提示注入)。工具级治理装饰器在函数层面强制执行策略...
official