能力标签
my-ai-tools MCP工具
🔌
MCP工具

my-ai-tools MCP工具

基于 Shell · 让 AI 助手直接操作你的系统与工具
英文名:my-ai-tools
⭐ 75 Stars 🍴 9 Forks 💻 Shell 📄 MIT 🏷 AI 7.2分
7.2AI 综合评分
MCP配置管理AI编码Claude自动化
✦ AI Skill Hub 推荐

AI Skill Hub 推荐使用:my-ai-tools MCP工具 是一款优质的MCP工具。AI 综合评分 7.2 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。

📚 深度解析

my-ai-tools MCP工具 是一款基于 MCP(Model Context Protocol)标准协议的 AI 工具扩展。MCP 协议由 Anthropic 开发并开源,旨在建立 AI 模型与外部工具之间的标准化通信接口,目前已被 Claude Desktop、Claude Code、Cursor 等主流 AI 工具采纳。

通过安装 my-ai-tools MCP工具,你的 AI 助手将获得额外的工具调用能力,可以用自然语言直接操控该工具的功能,无需学习复杂的命令行语法。MCP 工具的核心价值在于"一次配置,永久增强"——配置完成后,每次与 AI 对话时都可以无缝调用这些工具。

在技术实现上,MCP 工具通过标准的 JSON-RPC 协议与 AI 客户端通信,工具的功能以"工具列表"的形式暴露给 AI 模型,AI 可以按需调用。my-ai-tools MCP工具 提供了结构化的工具调用接口,使 AI 模型能够精确地理解和使用每个功能点,显著降低 AI 在工具使用上的错误率。

与传统的 API 集成相比,MCP 工具的优势在于无需编写代码——用户只需在配置文件中添加几行 JSON,即可让 AI 获得全新能力。AI Skill Hub 将 my-ai-tools MCP工具 评为 AI 评分 7.2 分,属于同类工具中的优质选择。

📋 工具概览

my-ai-tools MCP工具 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。

GitHub Stars
⭐ 75
开发语言
Shell
支持平台
macOS / Linux
维护状态
轻量级项目,按需更新
开源协议
MIT
AI 综合评分
7.2 分
工具类型
MCP工具
Forks
9

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理,如需查看完整原始文档请访问底部「原始来源」。

my-ai-tools MCP工具 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。

📌 核心特色
  • 通过标准 MCP 协议与 Claude、Cursor 等主流 AI 客户端深度集成
  • 提供结构化工具调用接口,显著降低 AI 集成复杂度
  • 支持 Claude Desktop 和 Claude Code 无缝接入,开箱即用
  • 可与其他 MCP 工具组合叠加,构建完整 AI 工作站
  • 轻量无侵入设计,不影响现有系统架构
🎯 主要使用场景
  • 在 Claude Desktop 对话中直接调用本地工具,实现 AI 与系统的深度联动
  • 通过自然语言驱动复杂的多步骤自动化任务,代替繁琐手动操作
  • 将多个 MCP 工具组合使用,构建个人专属 AI 工作站
以下安装命令基于项目开发语言和类型自动生成,实际以官方 README 为准。
安装命令
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/jellydn/my-ai-tools

# 方式二:手动配置 claude_desktop_config.json
{
  "mcpServers": {
    "my-ai-tools-mcp--": {
      "command": "npx",
      "args": ["-y", "my-ai-tools"]
    }
  }
}

# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
📋 安装步骤说明
  1. 确认已安装 Node.js(v18 或以上版本)
  2. 打开 Claude Desktop 或 Claude Code 的 MCP 配置文件
  3. 按「交给 Agent 安装 → Claude Desktop」标签中的 JSON 配置填入 mcpServers 字段
  4. 保存配置文件并重启 Claude 客户端
  5. 重启后,在对话中即可使用本工具
以下用法示例由 AI Skill Hub 整理,涵盖最常见的使用场景。
常用命令 / 代码示例
# 安装后在 Claude 对话中直接使用
# 示例:
用户: 请帮我用 my-ai-tools MCP工具 执行以下任务...
Claude: [自动调用 my-ai-tools MCP工具 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"
以下配置示例基于典型使用场景生成,具体参数请参照官方文档调整。
配置示例
// claude_desktop_config.json 配置示例
{
  "mcpServers": {
    "my-ai-tools_mcp__": {
      "command": "npx",
      "args": ["-y", "my-ai-tools"],
      "env": {
        // "API_KEY": "your-api-key-here"
      }
    }
  }
}

// 保存后重启 Claude Desktop 生效
📑 README 深度解析 真实文档 完整度 87/100 查看 GitHub 原文 →
以下内容由系统直接从 GitHub README 解析整理,保留代码块、表格与列表结构。

Welcome to my-ai-tools 👋

GitHub stars GitHub license PRs Welcome

Comprehensive configuration management for AI coding tools - Replicate my complete setup for Claude Code, OpenCode, fx, Muse Code, Amp, Kilo CLI, Codex, Devin CLI, Kimi Code, Gemini CLI, Antigravity CLI, Pi, Oh My Pi, GitHub Copilot CLI, Cursor Agent CLI, Factory Droid, Cline, Grok CLI, MiMo-Code, Qoder CLI, DeepSeek Harness, Kiro CLI, Delta, Hunk, Codiff, ctx, Open Code Review, CCS, and Reasonix with custom configurations, MCP servers, skills, plugins, and commands.

📖 View Documentation Website - Interactive landing page with full documentation and search.

✨ Features

  • 🚀 One-line installer - Get started in seconds
  • 🔄 Bidirectional sync - Install configs or export your current setup
  • 🤖 Multiple AI tools - Claude Code, OpenCode, fx, Muse Code, Amp, CCS, Devin, Kimi Code, Gemini, Antigravity, Grok, MiMo-Code, Qoder CLI, DeepSeek Harness, Kiro CLI, Delta, Hunk, Codiff, ctx, Open Code Review, Reasonix, and more
  • 🔌 MCP Server integration - Context7, Sequential-thinking, qmd, codebase-memory-mcp, agentmemory, sem, ctx
  • 🎯 Custom agents & skills - Pre-configured for maximum productivity
  • 🤝 Agent Teams - Coordinate specialized agents for complex workflows (code review, testing, docs)
  • 📦 Plugin support - Official and community plugins
  • 🛡️ Git Guard Hook - Prevents dangerous git commands (force push, hard reset, etc.)

📋 Prerequisites

Prerequisites for Windows

1. Git for Windows - Includes Git Bash (required for running shell scripts) - Download from: https://git-scm.com/download/win - During installation, choose "Use Git and optional Unix tools from the Command Prompt" to add Git Bash to PATH

2. jq (JSON processor) - Auto-installed via winget if available - Manual install: winget install -e --id jqlang.jq

Installation

curl -fsSL https://cli.devin.ai/install.sh | bash

Backup existing configs before installing

curl -fsSL https://ai-tools.itman.fyi/install.sh | bash -s -- --backup

Manual Installation

Clone the repository and run the installer:

git clone https://github.com/jellydn/my-ai-tools.git
cd my-ai-tools
./cli.sh

Options:

  • --dry-run - Preview changes without making them
  • --backup - Backup existing configs before installing
  • --no-backup - Skip backup prompt
  • -y / --yes - Non-interactive mode; only installs/configures your active tool set (amp, codex, ctx, cursor, fx, kilo, muse, opencode, open_code_review, pi, omp, antigravity, ai-switcher, claude, reasonix). Shared infra (plugins, skills, global tools) still installed. Auto-activated in CI/piped input.
  • --migrate-gemini - One-step Gemini→Antigravity CLI migration

Forward: Install to Home (`cli.sh`)

Copy configurations from this repository to your home directory (~/.claude/, ~/.config/opencode/, etc.):

./cli.sh [--dry-run] [--backup] [--no-backup] [-y|--yes] [--migrate-gemini]

Install and configure fx interactively

./cli.sh

Official macOS/Linux installer

curl -fsSL https://dev.meta.ai/install.sh | sh

🪟 Windows Installation

The installer supports Windows via PowerShell or Git Bash.

Installation

curl -fsSL https://claude.ai/install.sh | bash

MCP Servers Setup

Automatic Setup (Recommended)

Run the setup script to configure MCP servers:

./cli.sh

The script will prompt you to install each MCP server:

  • context7 - Documentation lookup for any library
  • sequential-thinking - Multi-step reasoning for complex analysis
  • qmd - Quick Markdown Search with AI-powered knowledge management
  • agentmemory - "Persistent memory" per the tool's branding; we use it session-only (qmd is the durable KB; see ~/.ai-tools/MEMORY.md)
  • fff - Fast file search with built-in memory for AI agents
  • react-grab-mcp - React component extraction and analysis
  • logpilot - AI-powered log analysis and tmux session monitoring

Manual Setup

For Claude Code

Configuration in ~/.claude/mcp-servers.json:

{
	"mcpServers": {
		"context7": {
			"command": "npx",
			"args": ["-y", "@upstash/context7-mcp@latest"]
		},
		"sequential-thinking": {
			"command": "npx",
			"args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]
		},
		"qmd": {
			"command": "qmd",
			"args": ["mcp"]
		},
		"agentmemory": {
			"command": "npx",
			"args": ["-y", "@agentmemory/mcp"]
		},
		"fff": {
			"type": "stdio",
			"command": "fff-mcp",
			"args": []
		},
		"react-grab-mcp": {
			"command": "npx",
			"args": ["-y", "@react-grab/mcp", "--stdio"]
		},
		"logpilot": {
			"command": "logpilot",
			"args": ["mcp-server"]
		}
	}
}

Or use the CLI (installed globally for all projects):

claude mcp add --scope user --transport stdio context7 -- npx -y @upstash/context7-mcp@latest
claude mcp add --scope user --transport stdio sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking
claude mcp add --scope user --transport stdio qmd -- qmd mcp
claude mcp add --scope user --transport stdio agentmemory -- npx -y @agentmemory/mcp
claude mcp add --scope user --transport stdio fff -- fff-mcp  # Requires: curl -fsSL https://dmtrkovalenko.dev/install-fff-mcp.sh | bash
claude mcp add --scope user --transport stdio logpilot -- logpilot mcp-server  # Requires: cargo install logpilot
claude mcp add --scope user --transport stdio sem -- sem-mcp  # Requires: cargo install --git https://github.com/Ataraxy-Labs/sem sem-mcp
Auto-Install: ./cli.sh automatically installs Rust via rustup when these cargo-dependent MCP servers are selected, so you don't need to install Rust manually beforehand (manual claude mcp add still requires a pre-installed Rust toolchain).
MCP Scopes: - --scope user (global): Available across all projects - --scope local (default): Only in current project directory - --scope project: Stored in .mcp.json for team sharing

Managing MCP Servers

```bash

If the above fails, check your Claude Code installation and subscription


#### Installation

The setup script (`./cli.sh`) automatically checks marketplace availability before installing plugins. If marketplace is unavailable, it will offer to install local plugins only.

**Automated installation (recommended):**
bash ./cli.sh # Includes marketplace check and fallback to local plugins

**Manual installation** (requires marketplace access):
bash

Plugin installation format: plugin-name@marketplace-name

then you install plugin 'plannotator' from that marketplace

claude plugin marketplace add backnotprop/plannotator claude plugin install plannotator@plannotator

claude plugin marketplace add jarrodwatts/claude-hud claude plugin install claude-hud@claude-hud

claude plugin marketplace add max-sixty/worktrunk claude plugin install worktrunk@worktrunk

claude plugin marketplace add openai/codex-plugin-cc claude plugin install codex@openai-codex

claude plugin marketplace add JuliusBrussee/caveman claude plugin install caveman@caveman

Install skills from this repository (jellydn/my-ai-tools)

Or install interactively (select which skills to install)

npx skills add jellydn/my-ai-tools --global --agent claude-code

Available skills: accountable-engineering, prd, ralph, qmd-knowledge, codemap, adr, handoffs, pickup, pr-review, slop, tdd, code-quality-review, commit-atomic, draft-pull-request, docs-update, llm-wiki, plannotator-setup-goal, portless-local, security-audit, tmux, blindspot-pass, implementation-logger, quiz-me, spec-interview, capability-experiments, code-review, context-discovery, doc-search, git-context, orchestrating-fusion

Agent Guidelines

Installed to ~/.config/devin/AGENTS.md with instructions for:

  • Session management with tmux
  • Using fff MCP for file search
  • Following best practices from ~/.ai-tools/best-practices.md
  • qmd knowledge management integration
  • Git safety guidelines

Usage

```bash

🚀 Quick Start

Example: The repository 'backnotprop/plannotator' registers as marketplace 'plannotator',

🎬 Demo

IT Man Channel

IT Man - My AI Setup in 2026

🖥️ Devin CLI (Optional)

Cognition AI's autonomous coding agent with deep cloud integration. Homepage | Docs

<details> <summary><strong>Installation & Configuration</strong></summary>

Configuration

Run the setup script to install configurations to ~/.config/devin/:

./cli.sh

The setup script automatically deploys MCP servers and agent guidelines.

🔄 Bidirectional Config Sync

𝒇x (Optional)

fx is a small native coding agent from Vercel Labs. The installer uses its official setup script on macOS and Linux, then installs this repository's global guidance to ~/.fx/AGENTS.md when fx is detected.

```bash

🎼 Muse Code (Optional)

Muse Code is Meta's coding agent for terminal and CI workflows, powered by Muse Spark 1.2. Meta brought it out of beta on August 31, 2026 with inter-session messaging, multi-agent workflows, safe conversation rewind, and a developer-preview SDK. Announcement | Docs | SDK

```bash

Add OPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_MODEL, and OPENAI_EMBEDDING_MODEL to .env

npm install npm run index # build data/index.json (server mode) npm run index:browser # build public/index-browser.json (browser mode) source .env # load OPENAI_BASE_URL for server mode npm run dev # serve http://localhost:3000 ```

The assistant only answers from the retrieved repository excerpts, cites the source file paths, and says "This is not documented in the repository." when the context is insufficient.

The landing page also has a browser mode that runs the embedding and an instruction-tuned model (Qwen2.5-Coder-0.5B-Instruct) in the browser via WebGPU. Browser mode downloads the ~9 MB index and the ~300 MB model on the user's device.

To pass options, download first, then run the local file:

irm https://ai-tools.itman.fyi/install.ps1 -OutFile install.ps1 .\install.ps1 -DryRun


**Local execution:**
powershell

Option 2: Git Bash

```bash

List all configured servers

claude mcp list

One-step Gemini→Antigravity CLI migration

curl -fsSL https://ai-tools.itman.fyi/install.sh | bash -s -- --migrate-gemini ```

Muse Code SDK (Developer Preview)

The SDK is a per-project TypeScript dependency, not another global CLI. It requires Node.js 20+ and a separately installed muse binary, which it launches as a local muse serve host over the Muse Session Protocol:

npm install @muse-code/sdk

The pre-1.0 SDK supports starting and resuming sessions, streaming responses, handling permission requests, and controlling the local Muse host. Minor releases can contain breaking changes during the developer preview.

Verify Claude CLI supports plugins

claude plugin list

🔌 MCP Servers & Plugins Overview

ToolMCP ServersPlugins/Extensions
**Claude Code**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctxOfficial + Community (plannotator, claude-hud, worktrunk, codex)
**OpenCode**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctx@plannotator/opencode
**Codex**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, node_repl, ctx-
**Kimi Code**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, logpilot, sem, ctxSkills, MCP servers, and hooks via ~/.kimi-code/
**Pi**context7, sequential-thinking, qmd, codebase-memory-mcp, fff, react-grab-mcp, agentmemory, sem, ctxPackages (pi-extension, pi-subagents, autoresearch, fff, mcp-adapter, simplify, rpiv-todo, btw, code-previews, codex-goal, commandcode-provider, pi-web-access, footer, tps-meter, pi-qwencloud-provider, pi-cursor-sdk)
**Oh My Pi**Pi-compatible layout; MCP servers via ~/.omp/agent/mcp.json when presentPi fork (@oh-my-pi/pi-coding-agent); configs managed under configs/omp/
**Muse Code**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctxWorkflows, session messaging, rewind, shared ~/.agents/skills, developer-preview SDK
**Amp**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctxAgent modes: fusion, glm-5.2, grok45, inkling, cursor-composer-2.5; plannotator; orca-agent-status
**Gemini**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctxDeprecated for Google One/unpaid tiers; migrate to Antigravity
**Antigravity**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctx (via plugin)my-ai-tools-gemini-migration
**Kilo**(uses OpenCode config)(uses OpenCode plugins)
**CommandCode**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctx-
**Copilot**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctx-
**Cursor**context7 (via bunx), sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctx-
**Conductor**Per-harness (Claude Code, Codex, Cursor MCP configs)Orchestrates parallel agents in isolated workspaces
**Factory**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctxcore, security-engineer, droid-evolved, autoresearch
**Orca**-Agent hooks (claude, gemini, codex, cursor, droid)
**Cline**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctxGlobal rules (AGENTS.md → ~/.cline/rules/, ~~/.agents/AGENTS.md), universal skills (~~/.agents/skills)
**Grok**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctxDefault model grok-4.5 (high reasoning); UI auto + rosepine-moon; Kanagawa theme staged
**MiMo-Code**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctx@plannotator/opencode, opencode-chrome-annotation
**Qoder CLI**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctx-
**DeepSeek Harness**context7, sequential-thinking, qmd, fff, sem, ctxCordis plugin composition; global AGENTS.md; native DeepSeek model route
**Kiro CLI**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctxSteering files (AGENTS.md), slash commands, MCP servers, ACP
**Reasonix**context7, sequential-thinking, qmd, codebase-memory-mcp, agentmemory, fff, react-grab-mcp, logpilot, sem, ctxDeepSeek-native; prefix-cache loop; [[plugins]] MCP in config.toml; ACP (reasonix acp); REASONIX.md/AGENTS.md memory; Kanagawa theme staged
**Delta**— (desktop app — model providers are configured in settings)Personal rules (~/.config/delta/AGENTS.md), isolated checkouts, collaborative threads
**Codiff**— (desktop app — uses configured agent backend via settings)

Plugins

Prerequisites

Before installing plugins, ensure:

  1. Claude Code subscription - Active subscription with plugin support
  2. Plugin marketplace access - Verify marketplace is enabled for your repository
  3. Network connectivity - Required for downloading marketplace plugins

To check marketplace availability:

```bash

Official plugins

claude plugin install typescript-lsp@claude-plugins-official claude plugin install pyright-lsp@claude-plugins-official claude plugin install context7@claude-plugins-official claude plugin install frontend-design@claude-plugins-official claude plugin install learning-output-style@claude-plugins-official claude plugin install swift-lsp@claude-plugins-official claude plugin install lua-lsp@claude-plugins-official claude plugin install code-simplifier@claude-plugins-official claude plugin install rust-analyzer-lsp@claude-plugins-official claude plugin install claude-md-management@claude-plugins-official

Community plugins (add marketplace first)

🇨🇳 中文文档镜像 AI 翻译 2026-05-30
英文原文章节由系统翻译为中文摘要,便于快速理解。完整原文见上方 "📑 README 深度解析"。
📌 简介

my-ai-tools 是一个专为开发者设计的全方位 AI 工具集成方案。它不仅集成了 Claude Code、Gemini、Antigravity 等多种强大的 AI 命令行工具,还通过 MCP (Model Context Protocol) 扩展了上下文感知能力。该项目旨在通过高度自动化的配置管理,为开发者提供一个开箱即用的终端 AI 工作环境。

⚡ 功能介绍

本项目具备极高的生产力特性:支持一键式安装与双向配置同步,方便在不同设备间迁移 AI 设置;内置 Taste Learning 功能,能够学习并遵循您的代码风格;深度集成多种 MCP Servers(如 Context7、Sequential-thinking),极大增强了 AI 的逻辑推理与文件处理能力;此外,还支持通过 Slash Commands(如 /review, /mcp)快速调用预设技能与 Agent Teams。

📋 环境依赖

在 Windows 环境下使用前,请确保已安装 Git for Windows(需包含 Git Bash),并在安装过程中选择“Use Git and optional Unix tools from the Command Prompt”以将 Git Bash 添加至 PATH。此外,系统还需要安装 jq 工具以处理 JSON 数据。对于其他系统,请确保具备基础的 Shell 环境及网络访问能力。

🛠 安装步骤(Docker/pip/源码)

推荐使用一键安装脚本进行部署,无需手动克隆仓库即可快速启动。在 Linux/macOS 上,可以使用 `curl` 命令直接运行安装脚本;在 Windows 上,推荐使用 PowerShell 脚本。为了保障数据安全,安装过程中支持 `--backup` 参数以备份现有配置。如果您希望手动控制,也可以通过 `git clone` 仓库后运行 `cli.sh` 进行安装,并支持 `--dry-run` 模式预览变更。

🚀 使用教程

项目设计为“终端优先”模式,非常适合习惯命令行操作的开发者。通过集成 Agent Guidelines,您可以让 AI 自动遵循特定的 Session 管理规范(如使用 tmux)和 Git 安全准则。您可以利用内置的指令与 Agent 进行交互,甚至通过特定的 MCP 工具实现文件搜索与知识管理(如 qmd)的无缝集成,实现高效的自动化开发流。

⚙️ 配置说明(含 MCP / env)

my-ai-tools 支持强大的双向配置同步功能,允许用户导出当前设置或安装预设配置。针对 Claude Code 等工具,用户可以通过插件机制扩展功能。在配置过程中,请确保您的 Claude Code 订阅支持插件功能,并已开启 Marketplace 访问权限。对于从 Gemini CLI 迁移的用户,可以使用 Antigravity CLI 的插件导入功能实现平滑过渡。

🔌 API 说明

本项目主要面向 CLI 工具链,通过集成 Claude CLI 和 Antigravity CLI 提供服务。用户可以通过 `claude plugin list` 等命令验证插件支持情况。需要注意的是,Google 正在将 Gemini CLI 用户迁移至 Antigravity CLI,建议开发者关注相关迁移通知,利用本项目提供的迁移插件实现配置的平滑转换。

🔄 工作流/模块

项目通过 MCP Servers 与 Plugins 的组合构建了完整的工作流。通过集成 context7、sequential-thinking、agentmemory 等 MCP 服务,Claude Code 等工具能够获得更强的逻辑思考与记忆能力。开发者可以根据需求管理��同的 Agent Skills,并通过插件扩展工具边界,实现从代码编写、评审到知识管理的闭环自动化体验。

🎯 aiskill88 AI 点评 A 级 2026-05-22

aiskill88点评:项目专注MCP工具配置管理,提供实用的自动化解决方案。Stars适中,Shell实现简洁高效,但文档完整度需关注,适合有基础的开发者使用。

📚 实用指南(长尾问题)
适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC,避免暴露公网
常见错误
  • API key 直接提交到 git 仓库(请用 .env 并加入 .gitignore)
  • MCP 配置路径拼错或权限不足,重启 Claude Desktop 才生效
部署方案
  • 云端托管:可放在 Vercel / Railway / Fly.io 等 PaaS 平台
相关搜索
my-ai-tools 中文教程my-ai-tools 安装报错怎么办my-ai-tools MCP 配置my-ai-tools 与同类工具对比my-ai-tools 最佳实践my-ai-tools 适合谁用

⚡ 核心功能

👥 适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
⭐ 最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC,避免暴露公网
⚠️ 常见错误
  • API key 直接提交到 git 仓库(请用 .env 并加入 .gitignore)
  • MCP 配置路径拼错或权限不足,重启 Claude Desktop 才生效

👥 适合人群

Claude Desktop / Claude Code 用户AI 工具开发者需要扩展 AI 能力的专业人士自动化工程师

🎯 使用场景

  • 在 Claude Desktop 对话中直接调用本地工具,实现 AI 与系统的深度联动
  • 通过自然语言驱动复杂的多步骤自动化任务,代替繁琐手动操作
  • 将多个 MCP 工具组合使用,构建个人专属 AI 工作站

⚖️ 优点与不足

✅ 优点
  • +MIT 协议,可免费商用
  • +标准化 MCP 协议,生态互联性强
  • +与 Claude 官方生态无缝对接
  • +即插即用,配置简单快捷
⚠️ 不足
  • 依赖 Claude 客户端,非 Claude 用户无法使用
  • MCP 协议仍在持续演进,接口可能变更
  • 需要一定的配置步骤
⚠️ 使用须知

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。

📄 License 说明

✅ 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。

🔗 相关工具推荐

📚 相关教程推荐
📰 相关 AI 新闻
🍿 AI 圈相关吃瓜
🗺️ 相关解决方案
🧩 你可能还需要
基于当前 Skill 的能力图谱,自动补全的工具组合

❓ 常见问题 FAQ

支持Claude、Codex等主流AI编码工具,可通过配置扩展支持更多工具。
💡 AI Skill Hub 点评

总体来看,my-ai-tools MCP工具 是一款质量良好的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。

⬇️ 获取与下载
⬇ 下载源码 ZIP

✅ MIT 协议 · 可免费商用 · 直接从 aiskill88 服务器下载,无需跳转 GitHub

📚 深入学习 my-ai-tools MCP工具
查看分步骤安装教程和完整使用指南,快速上手这款工具
🌐 原始信息
原始名称 my-ai-tools
原始描述 开源MCP工具:Comprehensive configuration management for AI coding tools - Replicate my comple。⭐75 · Shell
Topics MCP配置管理AI编码Claude自动化
GitHub https://github.com/jellydn/my-ai-tools
License MIT
语言 Shell
🔗 原始来源
🐙 GitHub 仓库  https://github.com/jellydn/my-ai-tools 🌐 官方网站  http://ai-tools.itman.fyi/

收录时间:2026-05-16 · 更新时间:2026-05-19 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。

📺 订阅 AI Skill Hub Daily Telegram 频道
每天 8 条精选 AI Skill、MCP、Agent 与自动化工具推送
加入频道 →