ai-coding-kit MCP server
Commit Nov 6, 2026Sync MCP servers, Agent Skills, and AI rules across multiple coding tools like Cursor, Claude Code, and Cline from a single local source.
Also known as i-stack/ai-coding-kit
- Stars
- 3
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 6, 2026
- License
- MIT
What is ai-coding-kit MCP?
ai-coding-kit syncs MCP servers, Agent Skills, and AI rules across multiple coding tools like Cursor, Claude Code, and Cline from a single local source.
Summary generated from the project's README
About ai-coding-kit MCP server
Managing MCP servers, Agent Skills, and AI rules across different coding environments is what this local-first toolkit enables for developers. It provides a single source of truth to define configurations, API keys, and platform settings, which then automatically sync to various AI coding hosts. This ensures that your specialized instructions and tool connections remain consistent whether you are working in Cursor, Claude Code, Cline, or Continue.
Users interact with the kit through a local installation process involving a shell script and a secrets file for API keys. The sync engine operates entirely on your local filesystem to inject secrets into MCP definitions and render them into native configuration formats for tools like CodeBuddy, Codex CLI, and Gemini CLI. Because the process is local-only, your sensitive credentials never leave your machine. The kit is primarily designed for macOS users and includes specialized modules for iOS engineers to manage Swift and SwiftUI rules.
What you can do with it
- 1Synchronize MCP configurationsDistribute your MCP server definitions and API keys to multiple AI coding tools simultaneously.
- 2Standardize iOS engineering rulesApply production-grade coding standards for Swift and SwiftUI across your AI agents.
- 3Maintain local knowledge basesUse a local embedded knowledge base with semantic search to manage plan reviews and entity graphs.
- 4Protect sensitive credentialsEnsure your API keys are injected into tool configurations without ever being uploaded to an external server.
Written from the project's README. Every use case is checked against a quote from it.
README
View on GitHubai-coding-kit
One kit. All your AI coding tools. Agent Skills management, MCP configuration sync, and iOS engineering rules — unified for Cursor, CodeBuddy, Codex, Claude Code, Gemini CLI, Continue, Cline, Qwen Code, and Xcode Coding Assistant.
ai-coding-kit is a local-first AI coding workflow toolkit. Define your MCP servers, API keys, Agent Skills, and platform settings once — auto-sync to every AI coding host you use.
面向 AI Coding / Agentic Coding / MCP（模型上下文协议）的多工具本地工程化工具包。为同时使用多个 AI 编码工具的开发者提供统一的 Agent Skill 维护、MCP 配置同步、iOS 工程规则和本地嵌入式知识库。
Quick Start
git clone https://github.com/i-stack/ai-coding-kit.git
cd ai-coding-kit
# 初始化本地配置（从 env/*.example 模板创建缺失文件，幂等）
bash install.sh
# 唯一需要编辑的文件：填入真实 API Keys / Tokens
$EDITOR env/secrets.json
# 一键同步
bash sync.sh
平台支持
当前主要开发和测试环境为 macOS。部分平台模块（如 Codex 同步中的 Xcode 集成、.zshrc 导出）在 macOS 外不可用。
欢迎 Windows 用户在 Windows 上验证并提交 PR。核心同步逻辑已尽量保持跨平台，适配改动预计较小。
🔒 纯本地同步，API 永不离机。 sync 引擎仅在你的本机文件系统内工作——将
env/secrets.json中的密钥注入 MCP 定义，渲染到各平台本地配置文件。不会上传任何数据到外部服务器，不会调用任何网络 API。 你的 API Key 始终只保存在这台机器上。可查看 sync 源码 。🔒 Local-only sync. Your API keys never leave this machine. The sync engine works entirely within your local filesystem — it reads secrets from
env/secrets.json, injects them into MCP definitions, and renders them into each platform's local config files. No data is uploaded to any external server. No network API is called. Your API keys stay on this machine, always. verify in the sync source code.
模块
各模块有独立的 README，按需深入：
| 模块 | 说明 | 文档 |
|---|---|---|
| skills-engineering/ | Agent Skill 内容源、多端同步、受控演进 | README |
| sync/ | MCP 配置同步引擎，注入 secrets 渲染到各平台原生格式 | README |
| env/ | 配置数据源（secrets + MCP 定义 + 平台配置） | README |
| skills-engineering/plan-reviews/ | Plan 知识库 —— 自动索引 plan-grill/cross-model-review 产物，语义搜索 + 实体图谱 | README |
| hooks/ | 项目钩子脚本（xmcp 初始化等） | README |
| .githooks/ | Git 提交/推送守卫（pre-commit + pre-push） | README |
Supported AI Coding Tools
| Tool | Synced Config |
|---|---|
| Cursor | .cursor/mcp.json |
| CodeBuddy | .codebuddy/mcp.json, models.json, skills/ |
| Claude Code | .claude.json, settings.json, skills/ |
| Codex CLI | .codex/config.toml |
| Gemini CLI | Environment variables |
| Continue | .continue/config.yaml |
| Cline (VSCode) | MCP settings JSON, skills/ |
| Qwen Code | settings.json env, skills/ |
| Xcode Coding Assistant | Codex + Claude Agent config paths |
安装 Git 钩子
bash install-hooks.sh
启用 pre-commit（规则变更结构/卫生守卫）和 pre-push（推送前强制同步校验）。详见 .githooks/README.md。
What is MCP?
Model Context Protocol (MCP) is an open protocol that lets AI coding tools connect to external services — GitHub, Playwright, databases, APIs, design tools — through a standardized interface. ai-coding-kit gives you one place to define all your MCP servers and syncs them to every tool that supports MCP.
Who This Is For
- Developers using multiple AI coding tools — define MCP servers and Agent Skills once, sync everywhere.
- iOS / Swift engineers — production-grade AI coding rules for Swift, SwiftUI, UIKit, concurrency, testing, and migration.
- AI infrastructure builders — local embedded knowledge base with semantic search and entity graph, zero external services.
- Team maintainers — single source of truth for MCP configuration, API keys, and model settings.
License
ai-coding-kit MCP questions
Is my data safe when syncing API keys?
Yes, the sync engine is local-only and works entirely within your local filesystem. No data is uploaded to external servers and no network APIs are called.
Which AI coding tools are supported?
It supports Cursor, CodeBuddy, Claude Code, Codex CLI, Gemini CLI, Continue, Cline, Qwen Code, and Xcode Coding Assistant.
What does this kit do for iOS engineers?
It provides production-grade AI coding rules specifically for Swift, SwiftUI, UIKit, concurrency, testing, and migration.