swift-mcp-server-generator
Generates a complete Swift server project using the official MCP SDK. It facilitates the creation of robust backends.
What it does
This generator creates a complete Swift server project for MCP communication. It sets up everything you need to start building a server that can understand and respond to commands.
When to use it
- ✓When you want to create a new Swift server for MCP.
- ✓When starting a project that requires structured communication with MCP.
- ✓To have a ready-to-use starting point for an MCP server.
Example of what to ask your AI
“Generate a Swift MCP server project.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
It uses an official Swift package called MCP Swift SDK to assemble the project structure. This includes files for defining tools, resources, and prompts, as well as a basic template for the server to function.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add github/awesome-copilot --skill swift-mcp-server-generatorOr download just the file:
curl -L https://raw.githubusercontent.com/github/awesome-copilot/main/skills/swift-mcp-server-generator/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Swift MCP Server Generator
Generate a complete, production-ready MCP server in Swift using the official Swift SDK package.
Project Generation
When asked to create a Swift MCP server, generate a complete project with this structure:
my-mcp-server/
├── Package.swift
├── Sources/
│ └── MyMCPServer/
│ ├── main.swift
│ ├── Server.swift
│ ├── Tools/
│ │ ├── ToolDefinitions.swift
│ │ └── ToolHandlers.swift
│ ├── Resources/
│ │ ├── ResourceDefinitions.swift
│ │ └── ResourceHandlers.swift
│ └── Prompts/
│ ├── PromptDefinitions.swift
│ └── PromptHandlers.swift
├── Tests/
│ └── MyMCPServerTests/
│ └── ServerTests.swift
└── README.md
Package.swift Template
// swift-tools-version: 6.0
import PackageDescription
let package = Package(
name: "MyMCPServer",
platforms: [
.macOS(.v13),
.iOS(.v16),
.watchOS(.v9),
.tvOS(.v16),
.visionOS(.v1)
],
dependencies: [
.package(
url: "https://github.com/modelcontextprotocol/swift-sdk.git",
from: "0.10.0"
),
.package(
url: "https://github.com/apple/swift-log.git",
from: "1.5.0"
),
.package(
url: "https://github.com/swift-server/swift-service-lifecycle.git",
from: "2.0.0"
)
],
targets: [
.executableTarget(
name: "MyMCPServer",
dependencies: [
.product(name: "MCP", package: "swift-sdk"),
.product(name: "Logging", package: "swift-log"),
.product(name: "ServiceLifecycle", package: "swift-service-lifecycle")
]
),
.testTarget(
name: "MyMCPServerTests",
dependencies: ["MyMCPServer"]
)
]
)
main.swift Template
import MCP
import Logging
import ServiceLifecycle
struct MCPService: Service {
let server: Server
let transport: Transport
func run() async throws {
try await server.start(transport: transport) { clientInfo, capabilities in
logger.info("Client connected", metadata: [
"name": .string(clientInfo.name),
"version": .string(clientInfo.version)
])
}
// Keep service running
try await Task.sleep(for: .days(365 * 100))
}
func shutdown() async throws {
logger.info("Shutting down MCP server")
await server.stop()
}
}
var logger = Logger(label: "com.example.mcp-server")
logger.logLevel = .info
do {
let server = await createServer()
let transport = StdioTransport(logger: logger)
let service = MCPService(server: server, transport: transport)
let serviceGroup = ServiceGroup(
services: [service],
configuration: .init(
gracefulShutdownSignals: [.sigterm, .sigint]
),
logger: logger
)
try await serviceGroup.run()
} catch {
logger.error("Fatal error", metadata: ["error": .string("\(error)")])
throw error
}
Server.swift Template
import MCP
import Logging
func createServer() async -> Server {
let server = Server(
name: "MyMCPServer",
version: "1.0.0",
capabilities: .init(
prompts: .init(listChanged: true),
resources: .init(subscribe: true, listChanged: true),
tools: .init(listChanged: true)
)
)
// Register tool handlers
await registerToolHandlers(server: server)
// Register resource handlers
await registerResourceHandlers(server: server)
// Register prompt handlers
await registerPromptHandlers(server: server)
return server
}
ToolDefinitions.swift Template
import MCP
func getToolDefinitions() -> [Tool] {
[
Tool(
name: "greet",
description: "Generate a greeting message",
inputSchema: .object([
"type": .string("object"),
"properties": .object([
"name": .object([
"type": .string("string"),
"description": .string("Name to greet")
])
]),
"required": .array([.string("name")])
])
),
Tool(
name: "calculate",
…
FAQ
What is MCP?
MCP is a protocol for communication between different software parts, allowing them to exchange information and commands in an organized way.
What are 'tools', 'resources', and 'prompts' in this context?
Tools are actions the server can perform. Resources are data the server can provide. Prompts are the questions or instructions the server can understand.
Do I need to know Swift programming to use this?
Yes, this generator creates a Swift project. Basic Swift knowledge is necessary to modify and use the generated code.
Details
Original description by the author
Generate a complete Model Context Protocol server project in Swift using the official MCP Swift SDK package.
repo: github/awesome-copilot
Popularity
- GitHub stars
- 40k
- Ranking position
- #5387
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
acquire-codebase-knowledge
Helps your agent understand and document an existing code project. It's useful for onboarding new people or getting an overview of the architecture.
github/awesome-copilot
acreadiness-assess
Enables your agent to assess a project's readiness for AI and generate a report. It's useful for understanding how well a project is prepared to use AI tools.
github/awesome-copilot
acreadiness-generate-instructions
Helps your agent create instructions for AI tools based on an assessment. It's useful for improving how AI interacts with code and closing identified gaps.
github/awesome-copilot
acreadiness-policy
Enables your agent to help define or apply policies for AI project assessment. It's useful for standardizing how projects are evaluated and ensuring compliance.
github/awesome-copilot
Similar skills
benchmark-optimization-loop
Has your agent improve something's speed in a measured way. It tests multiple versions and chooses the fastest one that still works correctly.
affaan-m/ECC
change-impact
Helps your agent analyze the impact of code changes before making them. It compares the planned vs. actual results afterward, covering paths, data, tests, and documentation. Useful for risky or system-wide changes.
affaan-m/ECC
click-path-audit
Lets your agent trace all user buttons and interactions to find bugs. It finds issues where functions seem to work alone but fail together. Useful when bugs persist even after debugging.
affaan-m/ECC