AGENT SKILL

kotlin-mcp-server-generator

Generate a complete Kotlin MCP server project with proper structure, dependencies, and implementation using the official io.modelcontextprotocol:kotlin-sdk library.

License 许可
MIT
最近更新
2026-11-13
Stars
★ 4.1w
Forks
5.3k

01 前言 Front Matter

name
kotlin-mcp-server-generator
description
Generate a complete Kotlin MCP server project with proper structure, dependencies, and implementation using the official io.modelcontextprotocol:kotlin-sdk library.

02 资源文件 4

03 SKILL.md 正文

Kotlin MCP Server Project Generator

Generate a complete, production-ready Model Context Protocol (MCP) server project in Kotlin.

Project Requirements

You will create a Kotlin MCP server with:

  1. Project Structure: Gradle-based Kotlin project layout
  2. Dependencies: Official MCP SDK, Ktor, and kotlinx libraries
  3. Server Setup: Configured MCP server with transports
  4. Tools: At least 2-3 useful tools with typed inputs/outputs
  5. Error Handling: Proper exception handling and validation
  6. Documentation: README with setup and usage instructions
  7. Testing: Basic test structure with coroutines

Template Structure

myserver/
├── build.gradle.kts
├── settings.gradle.kts
├── gradle.properties
├── src/
│   ├── main/
│   │   └── kotlin/
│   │       └── com/example/myserver/
│   │           ├── Main.kt
│   │           ├── Server.kt
│   │           ├── config/
│   │           │   └── Config.kt
│   │           └── tools/
│   │               ├── Tool1.kt
│   │               └── Tool2.kt
│   └── test/
│       └── kotlin/
│           └── com/example/myserver/
│               └── ServerTest.kt
└── README.md

build.gradle.kts Template

plugins {
    kotlin("jvm") version "2.1.0"
    kotlin("plugin.serialization") version "2.1.0"
    application
}

group = "com.example"
version = "1.0.0"

repositories {
    mavenCentral()
}

dependencies {
    implementation("io.modelcontextprotocol:kotlin-sdk:0.7.2")
    
    // Ktor for transports
    implementation("io.ktor:ktor-server-netty:3.0.0")
    implementation("io.ktor:ktor-client-cio:3.0.0")
    
    // Serialization
    implementation("org.jetbrains.kotlinx:kotlinx-serialization-json:1.7.3")
    
    // Coroutines
    implementation("org.jetbrains.kotlinx:kotlinx-coroutines-core:1.9.0")
    
    // Logging
    implementation("io.github.oshai:kotlin-logging-jvm:7.0.0")
    implementation("ch.qos.logback:logback-classic:1.5.12")
    
    // Testing
    testImplementation(kotlin("test"))
    testImplementation("org.jetbrains.kotlinx:kotlinx-coroutines-test:1.9.0")
}

application {
    mainClass.set("com.example.myserver.MainKt")
}

tasks.test {
    useJUnitPlatform()
}

kotlin {
    jvmToolchain(17)
}

settings.gradle.kts Template

rootProject.name = "{{PROJECT_NAME}}"

Main.kt Template

package com.example.myserver

import io.modelcontextprotocol.kotlin.sdk.server.StdioServerTransport
import kotlinx.coroutines.runBlocking
import io.github.oshai.kotlinlogging.KotlinLogging

private val logger = KotlinLogging.logger {}

fun main() = runBlocking {
    logger.info { "Starting MCP server..." }
    
    val config = loadConfig()
    val server = createServer(config)
    
    // Use stdio transport
    val transport = StdioServerTransport()
    
    logger.info { "Server '${config.name}' v${config.version} ready" }
    server.connect(transport)
}

Server.kt Template

package com.example.myserver

import io.modelcontextprotocol.kotlin.sdk.server.Server
import io.modelcontextprotocol.kotlin.sdk.server.ServerOptions
import io.modelcontextprotocol.kotlin.sdk.Implementation
import io.modelcontextprotocol.kotlin.sdk.ServerCapabilities
import com.example.myserver.tools.registerTools

fun createServer(config: Config): Server {
    val server = Server(
        serverInfo = Implementation(
            name = config.name,
            version = config.version
        ),
        options = ServerOptions(
            capabilities = ServerCapabilities(
                tools = ServerCapabilities.Tools(),
                resources = ServerCapabilities.Resources(
                    subscribe = true,
                    listChanged = true
                ),
                prompts = ServerCapabilities.Prompts(listChanged = true)
            )
        )
    ) {
        config.description
    }
    
    // Register all tools
    server.registerTools()
    
    return server
}

Config.kt Template

package com.example.myserver.config

import kotlinx.serialization.Serializable

@Serializable
data class Config(
    val name: String = "{{PROJECT_NAME}}",
    val version: String = "1.0.0",
    val description: String = "{{PROJECT_DESCRIPTION}}"
)

fun loadConfig(): Config {
    return Config(
        name = System.getenv("SERVER_NAME") ?: "{{PROJECT_NAME}}",
        version = System.getenv("VERSION") ?: "1.0.0",
        description = System.getenv("DESCRIPTION") ?: "{{PROJECT_DESCRIPTION}}"
    )
}

Tool1.kt Template

package com.example.myserver.tools

import io.modelcontextprotocol.kotlin.sdk.server.Server
import io.modelcontextprotocol.kotlin.sdk.CallToolRequest
import io.modelcontextprotocol.kotlin.sdk.CallToolResult
import io.modelcontextprotocol.kotlin.sdk.TextContent
import kotlinx.serialization.json.buildJsonObject
import kotlinx.serialization.json.put
import kotlinx.serialization.json.putJsonObject
import kotlinx.serialization.json.putJsonArray

fun Server.registerTool1() {
    addTool(
        name = "tool1",
        description = "Description of what tool1 does",
        inputSchema = buildJsonObject {
            put("type", "object")
            putJsonObject("properties") {
                putJsonObject("param1") {
                    put("type", "string")
                    put("description", "First parameter")
                }
                putJsonObject("param2") {
                    put("type", "integer")
                    put("description", "Optional second parameter")
                }
            }
            putJsonArray("required") {
                add("param1")
            }
        }
    ) { request: CallToolRequest ->
        // Extract and validate parameters
        val param1 = request.params.arguments["param1"] as? String
            ?: throw IllegalArgumentException("param1 is required")
        val param2 = (request.params.arguments["param2"] as? Number)?.toInt() ?: 0
        
        // Perform tool logic
        val result = performTool1Logic(param1, param2)
        
        CallToolResult(
            content = listOf(
                TextContent(text = result)
            )
        )
    }
}

private fun performTool1Logic(param1: String, param2: Int): String {
    // Implement tool logic here
    return "Processed: $param1 with value $param2"
}

tools/ToolRegistry.kt Template

package com.example.myserver.tools

import io.modelcontextprotocol.kotlin.sdk.server.Server

fun Server.registerTools() {
    registerTool1()
    registerTool2()
    // Register additional tools here
}

ServerTest.kt Template

package com.example.myserver

import kotlinx.coroutines.test.runTest
import kotlin.test.Test
import kotlin.test.assertEquals
import kotlin.test.assertFalse

class ServerTest {
    
    @Test
    fun `test server creation`() = runTest {
        val config = Config(
            name = "test-server",
            version = "1.0.0",
            description = "Test server"
        )
        
        val server = createServer(config)
        
        assertEquals("test-server", server.serverInfo.name)
        assertEquals("1.0.0", server.serverInfo.version)
    }
    
    @Test
    fun `test tool1 execution`() = runTest {
        val config = Config()
        val server = createServer(config)
        
        // Test tool execution
        // Note: You'll need to implement proper testing utilities
        // for calling tools in the server
    }
}

README.md Template

# {{PROJECT_NAME}}

A Model Context Protocol (MCP) server built with Kotlin.

## Description

{{PROJECT_DESCRIPTION}}

## Requirements

- Java 17 or higher
- Kotlin 2.1.0

## Installation

Build the project:

\`\`\`bash
./gradlew build
\`\`\`

## Usage

Run the server with stdio transport:

\`\`\`bash
./gradlew run
\`\`\`

Or build and run the jar:

\`\`\`bash
./gradlew installDist
./build/install/{{PROJECT_NAME}}/bin/{{PROJECT_NAME}}
\`\`\`

## Configuration

Configure via environment variables:

- `SERVER_NAME`: Server name (default: "{{PROJECT_NAME}}")
- `VERSION`: Server version (default: "1.0.0")
- `DESCRIPTION`: Server description

## Available Tools

### tool1
{{TOOL1_DESCRIPTION}}

**Input:**
- `param1` (string, required): First parameter
- `param2` (integer, optional): Second parameter

**Output:**
- Text result of the operation

## Development

Run tests:

\`\`\`bash
./gradlew test
\`\`\`

Build:

\`\`\`bash
./gradlew build
\`\`\`

Run with auto-reload (development):

\`\`\`bash
./gradlew run --continuous
\`\`\`

## Multiplatform

This project uses Kotlin Multiplatform and can target JVM, Wasm, and iOS.
See `build.gradle.kts` for platform configuration.

## License

MIT

Generation Instructions

When generating a Kotlin MCP server:

  1. Gradle Setup: Create proper build.gradle.kts with all dependencies
  2. Package Structure: Follow Kotlin package conventions
  3. Type Safety: Use data classes and kotlinx.serialization
  4. Coroutines: All operations should be suspending functions
  5. Error Handling: Use Kotlin exceptions and validation
  6. JSON Schemas: Use buildJsonObject for tool schemas
  7. Testing: Include coroutine test utilities
  8. Logging: Use kotlin-logging for structured logging
  9. Configuration: Use data classes and environment variables
  10. Documentation: KDoc comments for public APIs

Best Practices

  • Use suspending functions for all async operations
  • Leverage Kotlin's null safety and type system
  • Use data classes for structured data
  • Apply kotlinx.serialization for JSON handling
  • Use sealed classes for result types
  • Implement proper error handling with Result/Either patterns
  • Write tests using kotlinx-coroutines-test
  • Use dependency injection for testability
  • Follow Kotlin coding conventions
  • Use meaningful names and KDoc comments

Transport Options

Stdio Transport

val transport = StdioServerTransport()
server.connect(transport)

SSE Transport (Ktor)

embeddedServer(Netty, port = 8080) {
    mcp {
        Server(/*...*/) { "Description" }
    }
}.start(wait = true)

Multiplatform Configuration

For multiplatform projects, add to build.gradle.kts:

kotlin {
    jvm()
    js(IR) { nodejs() }
    wasmJs()
    
    sourceSets {
        commonMain.dependencies {
            implementation("io.modelcontextprotocol:kotlin-sdk:0.7.2")
        }
    }
}

04 同仓库更多 Skills

github
github/awesome-copilot

supabase-rls-policies

Write, review, and test Supabase Row Level Security (RLS) policies so that one user cannot read or change another user's rows. Use when creating or changing tables, policies, views, or security definer functions in a Supabase project, when reviewing a migration that touches RLS, or when asked to prove user isolation with pgTAP tests that sign in as two users.

测试与质量Skill与智能体开发
★ 4.1w
github
github/awesome-copilot

skill-distribution-audit

Audit a skill collection before release or investigate installer omissions, archived/template leakage, duplicate identities, and manifest drift. Reconcile the intended public source set, distribution manifest, and actual discovery output for a specified consumer version. Includes a deterministic set-comparison helper.

Skill与智能体开发
★ 4.1w
github
github/awesome-copilot

logicapps-custom-code-net10-migration

Migrate Azure Logic Apps Standard local-function custom-code projects from .NET 8 to .NET 10. Use for legacy Logic Apps custom-code workspace upgrades, project/package configuration, custom-worker settings, publication, and integrated VS Code debugging. Not for ordinary .NET applications, standalone Azure Functions, Consumption workflows, or cloud deployment.

开发工程师
★ 4.1w
github
github/awesome-copilot

winmd-api-search

Find and explore Windows desktop APIs. Use when building features that need platform capabilities — camera, file access, notifications, UI controls, AI/ML, sensors, networking, etc. Discovers the right API for a task and retrieves full type details (methods, properties, events, enumeration values).

开发工程师后端与接口
★ 4.1w
github
github/awesome-copilot

resemble-detect

Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using Resemble AI

后端与接口图像与多媒体
★ 4.1w
github
github/awesome-copilot

quality-playbook

Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with regression tests, executes a multi-model spec audit (Council of Three), and produces a consolidated bug report with TDD-verified patches. Finds the 35% of real defects that structural code review alone cannot catch. Works with any language. Trigger on 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', or 'coverage theater'.

代码审查Skill与智能体开发
★ 4.1w