AI Skill Hub 强烈推荐:AgentRunKit 是一款优质的MCP工具。AI 综合评分 8.0 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
AgentRunKit 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
AgentRunKit 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/Tom-Ryder/AgentRunKit
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"agentrunkit": {
"command": "npx",
"args": ["-y", "agentrunkit"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 AgentRunKit 执行以下任务... Claude: [自动调用 AgentRunKit MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"agentrunkit": {
"command": "npx",
"args": ["-y", "agentrunkit"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src="assets/logo-dark.png" alt="AgentRunKit" width="280"> </p>
<p align="center"> <a href="https://github.com/Tom-Ryder/AgentRunKit/actions/workflows/ci.yml"><img src="https://github.com/Tom-Ryder/AgentRunKit/actions/workflows/ci.yml/badge.svg" alt="CI"></a> <img src="https://img.shields.io/badge/Swift-6.0-orange" alt="Swift 6.0"> <img src="https://img.shields.io/badge/Platforms-iOS%2018%20%7C%20macOS%2015-blue" alt="Platforms"> <img src="https://img.shields.io/badge/On--Device-MLX%20%7C%20Foundation%20Models-8B5CF6" alt="On-Device MLX + Foundation Models"> <img src="https://img.shields.io/badge/SPM-compatible-brightgreen" alt="SPM"> <img src="https://img.shields.io/badge/License-MIT-lightgrey" alt="License"> <a href="https://swiftpackageindex.com/Tom-Ryder/AgentRunKit/documentation/agentrunkit"><img src="https://img.shields.io/badge/Documentation-DocC-blue" alt="Documentation"></a> </p>
<p align="center"> A Swift 6 SDK for building LLM-powered agents with type-safe tool calling. </p>
<p align="center"> <b>Zero-dependency core</b> · <b>Full Sendable</b> · <b>Async/await</b> · <b>Cloud + Local</b> · <b>MCP</b> </p>
---
AsyncThrowingStream and @Observable SwiftUI wrapper---
| Platform | Version |
|---|---|
| iOS | 18.0+ |
| macOS | 15.0+ |
| Swift | 6.0+ |
| Xcode | 26+ for local development and CI |
---
Add to your Package.swift:
dependencies: [
.package(url: "https://github.com/Tom-Ryder/AgentRunKit.git", from: "2.4.0")
]
.target(name: "YourApp", dependencies: ["AgentRunKit"])
For on-device inference, additional targets are available:
AgentRunKitMLX for MLX on Apple Silicon (links mlx-swift-lm)AgentRunKitFoundationModels for Apple Foundation Models (iOS 26+ and macOS 26+, no external dependencies)---
import AgentRunKit
let client = OpenAIClient.openAI(apiKey: "sk-...", model: "gpt-5.4")
let weatherTool = try Tool<WeatherParams, String, EmptyContext>(
name: "get_weather",
description: "Get the current weather"
) { params, _ in
"72°F and sunny in \(params.city)"
}
let agent = Agent(client: client, tools: [weatherTool])
let result = try await agent.run(userMessage: "What's the weather in SF?", context: EmptyContext())
if let content = result.content {
print(content)
}
result.content is optional. Completed runs return finish-tool content, while structural terminal reasons such as max iterations or token budget exhaustion surface through result.finishReason with no final content.
---
Examples/AgentCode is an interactive terminal coding agent built with AgentRunKit. It demonstrates the full agent loop in a local workspace: streaming events, type-safe tools, approval-gated edits and command execution, bounded file access, transcript export, and deterministic offline mode.
cd Examples/AgentCode
swift run agent-code
By default it opens a bundled broken Swift package so you can ask it to fix failing tests. Set OPENAI_API_KEY for a live OpenAI-compatible provider, or run without a key to exercise the CLI with the offline test client.
---
AgentRunKit是一个高质量的开源MCP工具,支持Swift 6 agent SDK
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,AgentRunKit 是一款质量优秀的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | AgentRunKit |
| Topics | mcpagent-sdkai-agentsanthropicapple-silicon |
| GitHub | https://github.com/Tom-Ryder/AgentRunKit |
| License | MIT |
| 语言 | Swift |
收录时间:2026-06-10 · 更新时间:2026-06-10 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端