skills-manager-mcp
Acts as a personal AI development environment manager, enabling workspace bootstrapping, headless skill and bundle installation, global caching, and health diagnostics.
README
Skills Manager MCP Server & CLI (skills-manager-mcp)
A production-ready CLI tool and Model Context Protocol (MCP) server for Antigravity Desktop that acts as your personal AI development environment manager.
It features zero-config automatic first-run initialization, workspace detection, headless skill & bundle installation, global skill caching, personal skill collection merging, schema version migrations, and health diagnostics.
Installation
Install globally using standard npm or pnpm (no extra security flags or install script approvals required):
npm install -g skills-manager-mcp
Automatic First-Run Initialization
skills-manager-mcp does not rely on npm postinstall lifecycle scripts (which npm security policies often block).
Instead, the very first time you run any command:
skills-manager-mcp status
(or when Antigravity Desktop invokes any MCP tool), the tool automatically detects first-time usage and configures itself:
Skills Manager MCP first-time setup detected...
✓ Global storage initialized: C:\Users\<username>\.ai-skills
✓ Skills cache ready: C:\Users\<username>\.ai-skills\cache
✓ Antigravity MCP registered: C:\Users\<username>\.gemini\antigravity-ide\mcp.json
✓ Server executable path: C:\Users\<username>\AppData\Roaming\npm\node_modules\skills-manager-mcp\dist\index.js
Initialization complete.
Subsequent executions skip initialization instantly because all configurations are already verified and active!
CLI Commands
1. skills-manager-mcp status
Displays the status dashboard (global config presence, cache statistics, Antigravity MCP registration status, detected workspace, and installed skills). Triggers auto-initialization on first run.
2. skills-manager-mcp doctor
Runs diagnostic health checks on your installation, configuration, global cache, and MCP registration.
skills-manager-mcp doctor
Example Output:
Skills Manager Doctor
✓ dist/index.js exists
✓ Antigravity configuration exists
✓ MCP path valid
✓ Global cache available
✓ skills.config.json valid
Everything is healthy.
3. skills-manager-mcp bootstrap
Prepares the current project workspace automatically.
- Detects active workspace
- Creates
.agents/skills/ - Merges personal (
~/.ai-skills/skills.config.json) and project skills - Installs skills/bundles headlessly from global cache or remote Git repositories
- Updates version metadata tracker (
.agents/skills-manager.json)
4. skills-manager-mcp sync
Synchronizes current workspace skills with your global personal collection (~/.ai-skills/skills.config.json).
5. skills-manager-mcp remove <skill1> [skill2]
Removes one or an array of specified skills or bundles from the project workspace .agents/skills.
- Option
--from-configalso removes them fromskills.config.jsonto prevent auto-reinstallation.
# Remove single skill
skills-manager-mcp remove find-skills
# Batch remove multiple skills & bundles
skills-manager-mcp remove find-skills frontend-design mattpocock-skills --from-config
6. skills-manager-mcp setup
Re-run setup & Antigravity MCP registration manually anytime.
Configuration (~/.ai-skills/skills.config.json)
You can manage your master list of skills and bundles globally at C:\Users\<username>\.ai-skills\skills.config.json:
{
"skills": [
{
"type": "skill",
"name": "find-skills",
"repository": "https://github.com/vercel-labs/skills",
"skill": "find-skills"
},
{
"type": "skill",
"name": "frontend-design",
"repository": "https://github.com/anthropics/skills",
"skill": "frontend-design"
},
{
"type": "bundle",
"name": "mattpocock-skills",
"repository": "https://github.com/mattpocock/skills"
}
]
}
MCP Server Tools Reference
When running inside Antigravity Desktop, the following MCP tools are available:
bootstrap_project: Prepares active workspace with skills and bundles.sync_skills: Synchronizes workspace skills with personal collection.install_skills: Installs missing skills and bundles.remove_skills: Removes one or an array of specified skills/bundles from workspace.list_installed_skills: Lists installed skills and bundle details.check_missing_skills: Checks status of skills/bundles.get_workspace_info: Debugging tool for inspecting workspace resolution.
Development & Testing Commands
# Install dependencies
pnpm install
# Run unit tests
pnpm test
# Compile TypeScript (generates dist/index.js and dist/cli.js)
pnpm run build
# Create npm distribution tarball
npm pack
# Link locally for testing
npm link
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。