MCP cover image
See in Github
2025-03-21

4

Github Watches

16

Github Forks

158

Github Stars

MCP Swift SDK!

Build & Deploy Coverage Statusodecov Buy me a coffee

Swift implementation of the Model Context Protocol (MCP), providing both client and server capabilities for integrating with LLM surfaces.

Overview

The Model Context Protocol allows applications to provide context for LLMs in a standardized way, separating the concerns of providing context from the actual LLM interaction. This Swift SDK implements the full MCP specification for the client, making it easy to:

  • Build MCP clients that can connect to any MCP server
  • Use standard transports like stdio and SSE
  • Handle all MCP protocol messages and lifecycle events

Installation

  • Xcode: File → Add Package Dependencies… and input the package URL https://github.com/gsabran/mcp-swift-sdk

  • SPM-based projects: Add the dependency to your package:

dependencies: [
  .package(url: "https://github.com/gsabran/mcp-swift-sdk", from: "0.2.0")
]

And then add the product that you need to all targets that use the dependency:

.product(name: "MCPServer", package: "mcp-swift-sdk"),
// and/or
.product(name: "MCPClient", package: "mcp-swift-sdk"),

Quick Start

⚠️ When using stdio servers in a MacOS app, you need to disable sandboxing. This is because the app will need to run the processes for each server.

Creating a Server

import MCPServer

let server = try await MCPServer(
  info: Implementation(name: "test-server", version: "1.0.0"),
  capabilities: .init(...),
  transport: .stdio())

// The client's roots, if available.  
let roots = await server.roots.value

// Keep the process running until the client disconnects.
try await server.waitForDisconnection()

Tool calling

The tool input schema can be generated for you (thanks swift-json-schema!)

import JSONSchemaBuilder

@Schemable
struct ToolInput {
  let text: String
}

let capabilities = ServerCapabilityHandlers(tools: [
  Tool(name: "repeat") { (input: ToolInput) in
    [.text(.init(text: input.text))]
  },
])

Creating a Client

import MCPClient

let transport = try Transport.stdioProcess(
  serverInfo.executable,
  args: serverInfo.args,
  env: serverInfo.env)
  
let client = try await MCPClient(
  info: .init(name: "example-client", version: "1.0.0"),
  transport: transport,
  capabilities: .init(
    roots: .init(info: .init(listChanged: true), handler: listRoots)))

// List available resources
let resources = await client.resources.value

// Read a specific resource
let resourceContent = try await client.readResource(uri: "file:///example.txt")

Documentation

License

This project is licensed under the MIT License—see the LICENSE file for details.

相关推荐

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Yusuf Emre Yeşilyurt
  • I find academic articles and books for research and literature reviews.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Carlos Ferrin
  • Encuentra películas y series en plataformas de streaming.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • lumpenspace
  • Take an adjectivised noun, and create images making it progressively more adjective!

  • https://appia.in
  • Siri Shortcut Finder – your go-to place for discovering amazing Siri Shortcuts with ease

  • apappascs
  • Entdecken Sie die umfassendste und aktuellste Sammlung von MCP-Servern auf dem Markt. Dieses Repository dient als zentraler Hub und bietet einen umfangreichen Katalog von Open-Source- und Proprietary MCP-Servern mit Funktionen, Dokumentationslinks und Mitwirkenden.

  • jae-jae
  • MCP -Server für den Fetch -Webseiteninhalt mit dem Headless -Browser von Dramatikern.

  • Mintplex-Labs
  • Die All-in-One-Desktop & Docker-AI-Anwendung mit integriertem Lappen, AI-Agenten, No-Code-Agent Builder, MCP-Kompatibilität und vielem mehr.

  • ravitemer
  • Ein leistungsstarkes Neovim -Plugin für die Verwaltung von MCP -Servern (Modellkontextprotokoll)

  • patruff
  • Brücke zwischen Ollama und MCP -Servern und ermöglicht es lokalen LLMs, Modellkontextprotokoll -Tools zu verwenden

  • pontusab
  • Die Cursor & Windsurf -Community finden Regeln und MCPs

  • WangRongsheng
  • 🧑‍🚀 全世界最好的 llm 资料总结(数据处理、模型训练、模型部署、 O1 模型、 MCP 、小语言模型、视觉语言模型) | Zusammenfassung der weltbesten LLM -Ressourcen.

  • n8n-io
  • Fair-Code-Workflow-Automatisierungsplattform mit nativen KI-Funktionen. Kombinieren Sie visuelles Gebäude mit benutzerdefiniertem Code, SelbstHost oder Cloud, 400+ Integrationen.

  • av
  • Führen Sie mühelos LLM -Backends, APIs, Frontends und Dienste mit einem Befehl aus.

    Reviews

    1 (1)
    Avatar
    user_ANK09wVX
    2025-04-17

    As a dedicated user of the mcp application, I am thoroughly impressed with the mcp-swift-sdk by gsabran. It significantly simplifies the integration of MCP functionalities into any Swift project, making development much smoother and more efficient. The comprehensive documentation and well-structured codebase are commendable. If you're looking to enhance your Swift app with powerful MCP features, I highly recommend checking it out. This SDK has certainly exceeded my expectations!