Kotlin-Mcp-Server
Kotlin-Mcp-Server是一款code方向的AI技能，核心价值是Best practices and patterns for building Model Context Protocol (MCP) servers in Kotlin using the official io，可用于解决开发者在code领域的实际问题，帮助用户提升效率、自动化重复任务或优化工作流。
Best practices and patterns for building Model Context Protocol (MCP) servers in Kotlin using the official io.modelcontextprotocol:kotlin-sdk library.
mkdir -p ./skills/kotlin-mcp-server && curl -sfL https://raw.githubusercontent.com/github/awesome-copilot/main/skills/kotlin-mcp-server/SKILL.md -o ./skills/kotlin-mcp-server/SKILL.mdRun in terminal / PowerShell. Requires curl (Unix) or PowerShell 5+ (Windows).
Skill Content
# Kotlin MCP Server Development Guidelines
When building MCP servers in Kotlin, follow these best practices and patterns using the official Kotlin SDK.
Server Setup
Create an MCP server using the `Server` class:
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
val server = Server(
serverInfo = Implementation(
name = "my-server",
version = "1.0.0"
),
options = ServerOptions(
capabilities = ServerCapabilities(
tools = ServerCapabilities.Tools(),
resources = ServerCapabilities.Resources(
subscribe = true,
listChanged = true
),
prompts = ServerCapabilities.Prompts(listChanged = true)
)
)
) {
"Server description goes here"
}Adding Tools
Use `server.addTool()` to register tools with typed request/response handling:
import io.modelcontextprotocol.kotlin.sdk.CallToolRequest
import io.modelcontextprotocol.kotlin.sdk.CallToolResult
import io.modelcontextprotocol.kotlin.sdk.TextContent
server.addTool(
name = "search",
description = "Search for information",
inputSchema = buildJsonObject {
put("type", "object")
putJsonObject("properties") {
putJsonObject("query") {
put("type", "string")
put("description", "The search query")
}
putJsonObject("limit") {
put("type", "integer")
put("description", "Maximum results to return")
}
}
putJsonArray("required") {
add("query")
}
}
) { request: CallToolRequest ->
val query = request.params.arguments["query"] as? String
?: throw IllegalArgumentException("query is required")
val limit = (request.params.arguments["limit"] as? Number)?.toInt() ?: 10
// Perform search
val results = performSearch(query, limit)
CallToolResult(
content = listOf(
TextContent(
text = results.joinToString("\n")
)
)
)
}Adding Resources
Use `server.addResource()` to provide accessible data:
import io.modelcontextprotocol.kotlin.sdk.ReadResourceRequest
import io.modelcontextprotocol.kotlin.sdk.ReadResourceResult
import io.modelcontextprotocol.kotlin.sdk.TextResourceContents
server.addResource(
uri = "file:///data/example.txt",
name = "Example Data",
description = "Example resource data",
mimeType = "text/plain"
) { request: ReadResourceRequest ->
val content = loadResourceContent(request.uri)
ReadResourceResult(
contents = listOf(
TextResourceContents(
text = content,
uri = request.uri,
mimeType = "text/plain"
)
)
)
}Adding Prompts
Use `server.addPrompt()` for reusable prompt templates:
import io.modelcontextprotocol.kotlin.sdk.GetPromptRequest
import io.modelcontextprotocol.kotlin.sdk.GetPromptResult
import io.modelcontextprotocol.kotlin.sdk.PromptMessage
import io.modelcontextprotocol.kotlin.sdk.Role
server.addPrompt(
name = "analyze",
description = "Analyze a topic",
arguments = listOf(
PromptArgument(
name = "topic",
description = "The topic to analyze",
required = true
)
)
) { request: GetPromptRequest ->
val topic = request.params.arguments?.get("topic") as? String
?: throw IllegalArgumentException("topic is required")
GetPromptResult(
description = "Analyze the given topic",
messages = listOf(
PromptMessage(
role = Role.User,
content = TextContent(
text = "Analyze this top🎯 Best For
- UI designers
- Product designers
- Claude users
- GitHub Copilot users
- Software engineers
💡 Use Cases
- Generating component mockups
- Creating design system tokens
- Code quality improvement
- Best practice enforcement
📖 How to Use This Skill
- 1
Install the Skill
Copy the install command from the Terminal tab and run it. The SKILL.md file downloads to your local skills directory.
- 2
Load into Your AI Assistant
Open Claude or GitHub Copilot and reference the skill. Paste the SKILL.md content or use the system prompt tab.
- 3
Apply Kotlin-Mcp-Server to Your Work
Open your project in the AI assistant and ask it to apply the skill. Start with a small module to verify the output quality.
- 4
Review and Refine
Review AI suggestions before committing. Run tests, check for regressions, and iterate on the skill output.
❓ Frequently Asked Questions
Does this work with Figma?
Some design skills integrate with Figma plugins. Check the Works With section for supported tools.
Is Kotlin-Mcp-Server compatible with Cursor and VS Code?
Yes — this skill works with any AI coding assistant including Cursor, VS Code with Copilot, and JetBrains IDEs.
Do I need specific dependencies for Kotlin-Mcp-Server?
Check the install command and Works With section. Most code skills only require the AI assistant and your codebase.
How do I install Kotlin-Mcp-Server?
Copy the install command from the Terminal tab and run it. The skill downloads to ./skills/kotlin-mcp-server/SKILL.md, ready to use.
Can I customize this skill for my team?
Absolutely. Edit the SKILL.md file to add team-specific instructions, examples, or workflows.
⚠️ Common Mistakes to Avoid
Skipping usability testing
AI-generated designs should be validated with real users before development.
Skipping validation
Always test AI-generated code changes, even for simple refactors.
Missing dependency updates
Check if the skill requires updated dependencies or new packages.