superskills-mcp
A general-purpose MCP gateway that exposes your local CLI skills to any AI assistant.
README
⚡ superskills-mcp
<div align="center"> <p><strong>A Universal, Agent-Agnostic MCP Gateway for Local Scripts & CLI Tools</strong></p> </div>
superskills-mcp is a lightweight, globally installable Model Context Protocol (MCP) gateway. It allows you to effortlessly expose your local bash scripts, python tools, or Node.js skills to any AI assistant (ChatGPT, Claude Desktop, Cursor, etc.) via a unified interface.
Instead of writing a custom MCP server for every small script you create, superskills-mcp acts as a dynamic registry. You simply drop your skill's path into the configuration, and it is instantly available to the AI.
✨ Key Features
- 🌍 Global Installation: Run it from anywhere on your system via the
superskills-mcpCLI. - 🔌 Dynamic Tool Registration: Add or remove skills dynamically without touching the server code.
- 🔄 Hot Reloading: Apply configuration changes on the fly with zero downtime using
superskills-mcp reload. - 📝 Native Logging: Built-in background daemon management and real-time log tailing.
- 🛡️ Secure Execution: Strict path validations, restricted runner boundaries, and input schema validation via Zod.
- 🌐 Multi-Transport Support: Expose tools over HTTP (for ChatGPT/Ngrok) or Stdio (for local Claude/Cursor).
- 📊 Web Dashboard: An integrated, premium dark-themed UI to monitor tool usage, toggle skills, and manage your local environment.
🚀 Quick Start
1. Installation
Install the CLI tool globally via npm or pnpm:
npm install -g superskills-mcp
2. Initialization
Generate your global configuration file (this will safely create ~/.superskills/mcp-config.json):
superskills-mcp init
3. Start the Gateway
Launch the MCP server in the background:
superskills-mcp serve &
(You can verify it is running by typing superskills-mcp status or by checking curl http://127.0.0.1:8787/health)
🛠️ CLI Reference
superskills-mcp comes with a powerful suite of management commands akin to PM2 or Nginx:
| Command | Description |
|---|---|
superskills-mcp init |
Initialize the global config at ~/.superskills/mcp-config.json. |
superskills-mcp serve |
Start the MCP server using the global config. |
superskills-mcp status |
Check if the server is actively running in the background. |
superskills-mcp stop |
Gracefully terminate the running server. |
superskills-mcp reload |
Smoothly restart the server to apply configuration changes instantly. |
superskills-mcp list |
Print a formatted list of all currently registered skills. |
superskills-mcp add <path> |
Auto-parse and add a new local skill directory to your global config. |
superskills-mcp remove <name> |
Unregister a skill from your global config by its name. |
superskills-mcp log |
Tail the real-time background logs ([INFO] and [ERROR]). |
📊 Web Dashboard
superskills-mcp 现在内置了一个精美的 Web 控制面板。你可以通过它实时监控技能的调用次数,并随时开启或禁用特定的技能。
- 确保服务器正在运行 (
superskills-mcp serve &)。 - 在浏览器中打开:
http://127.0.0.1:8787/dashboard/
该面板完全集成在 Express 服务器中,无需安装任何额外依赖,即插即用。
📦 Managing Skills
Adding Skills Automatically
You can use the CLI to dynamically attach a new local skill:
superskills-mcp add /path/to/your/custom_skill
Note: This command extracts the skill name and description, but sets the input schema to {}. If your skill requires specific arguments (like url or query), open ~/.superskills/mcp-config.json and define the JSON schema under the input key.
Removing Skills
To detach a skill:
superskills-mcp remove my_custom_skill
Applying Changes
After adding, removing, or manually editing your config, reload the gateway:
superskills-mcp reload
🔍 Auto-Discovery (Zero Configuration)
If you have a collection of skills in a folder, you can let superskills-mcp discover them automatically.
Any sub-directory containing a SKILL.md file will be recognized as a tool.
- Open
~/.superskills/mcp-config.json. - Add
scanRootsandscanSettings:
{
"scanRoots": [
"~/.baoyu-skills/skills"
],
"scanSettings": {
"watch": true,
"ignore": ["node_modules", ".git"]
}
}
scanRoots: An array of directories to scan for sub-folders containingSKILL.md.watch: Iftrue, the server will monitor these directories in real-time. Adding or removing a folder will instantly update the available tools for your AI assistant—no restart required.
⚙️ Configuration File Structure
Your global configuration lives at ~/.superskills/mcp-config.json.
{
"server": {
"name": "superskills-mcp",
"version": "0.5.0",
"transport": "http",
"host": "127.0.0.1",
"port": 8787
},
"defaults": {
"timeoutMs": 120000,
"maxOutputBytes": 10485760,
"runner": {
"command": "bun",
"args": ["{serverDir}/scripts/mcp-adapter.ts"]
}
},
"skills": [
{
"name": "read_x_to_markdown",
"description": "Read a given X/Twitter link and return clean Markdown.",
"skillDir": "/Users/username/my-skills/twitter-scraper",
"input": {
"url": {
"type": "string",
"format": "uri",
"description": "X/Twitter post URL to read"
}
},
"env": {
"KEEP_OUTPUT": "false"
}
}
]
}
defaults.runner.args: The{serverDir}placeholder is automatically replaced with this gateway's actual installation path.skills[].input: Defines the exact JSON schema that the AI must fulfill when calling your tool.skills[].env: Environment variables scoped specifically to that single skill's execution.
🔗 Connecting AI Assistants
🌐 Connecting to ChatGPT (HTTP Transport)
For cloud-based AI like ChatGPT, the server must be exposed to the internet.
- Ensure the gateway is running (
superskills-mcp serve &). - Expose the local port via a persistent Ngrok tunnel:
ngrok http --domain=your-free-static-domain.ngrok-free.app 8787
- In your ChatGPT MCP Configuration, provide the proxy URL with the
/mcppath:https://your-free-static-domain.ngrok-free.app/mcp
Tip: You can test if the proxy is bypassing Ngrok's browser warnings by running:
curl -H "ngrok-skip-browser-warning: true" https://your-free-static-domain.ngrok-free.app/health
🖥️ Connecting to Claude Desktop / Cursor (Stdio Transport)
Local clients prefer communicating via standard input/output (stdio). You do not need to run serve & manually for these clients; they will spawn the gateway themselves.
Add this block to your local client config (e.g., ~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"superskills-mcp": {
"command": "superskills-mcp",
"args": ["serve", "--transport", "stdio"]
}
}
}
🔒 Security Principles
- Isolated Execution: Skills are executed using restricted runners without shell interpolation (
shell: false), eliminating command injection risks. - Directory Verification: The gateway strictly validates that runner scripts exist within the trusted
serverDiror the specificskillDir. - Resource Limits: Configurable
timeoutMsandmaxOutputBytesprevent runaway scripts from crashing your system.
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。