Which integrations are available for this server?

Integrates with Google Labs' developer tools and AI services, offering capabilities for building and automating Google-based workflows. Integrates skills and tools from Vercel's ecosystem, enabling AI agents to manage and deploy Vercel projects and serverless functions.

How do I use SkillsWebMcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SkillsWebMcp search for a skill to debug TypeScript errors" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

de en es ja ko ru zh

SkillsWebMcp

by AbinashBalaraman

Overview Schema Related Servers Score Discussions

TypeScript

Remote

SkillsWebMcp 🌐⚡

High-Performance WebMCP (W3C Draft) & Model Context Protocol Bridge for Developer Skills

SkillsWebMcp is a production-grade WebMCP and Model Context Protocol (MCP) bridge server that indexes, manages, and executes 1,000+ developer agent skills and tools from top open-source engineering ecosystems (Anthropic, VoltAgent, Microsoft, Vercel, Google Labs, Composio, and specialized developer suites).

It brings the next-generation WebMCP in-browser agent tool calling standard directly to web clients while simultaneously providing a native MCP JSON-RPC bridge for IDEs (Claude Desktop, Cursor IDE, Windsurf, Zed).

✨ Features

⚡ Dual MCP & WebMCP Architecture:
- Model Context Protocol (MCP): Full JSON-RPC 2.0 Server-Sent Events (/api/mcp/sse) and HTTP message endpoint (/api/mcp/message).
- WebMCP (W3C Draft Standard): Exposes document.modelContext and navigator.modelContext for in-browser AI tool execution and DOM automation.
🧠 Intelligent Progressive Disclosure:
- Dynamic Top-20 (Recommended): Loads a lightweight meta-tool (search_and_load_agent_skills) that allows the model to dynamically search and mount tools into memory on demand. Saves 98.4% of context tokens.
- Selective Category: Mounts only tools in a specific engineering domain (e.g. TypeScript & Architecture, Security & Testing, AI & LLMs).
- Full Catalog: Exposes all registered tools for massive context models.
🔌 1-Click Client Integration:
- Pre-generated configuration snippets for Claude Desktop, Cursor IDE, Windsurf, Zed Editor, Continue.dev, and LibreChat.
🔍 Live MCP Inspector & Tester:
- In-browser interactive JSON Schema inspector to test tool invocations and validate parameter schemas with real-time response logs.
🔄 Automated 24-Hour Background Synchronizer:
- Background daemon that checks upstream repositories, updates tool definitions, and verifies schema contracts.
🎨 Modern Developer UI:
- Fast, responsive dashboard built with React 19, Tailwind CSS, Lucide Icons, and Motion transitions.

🏗️ Architecture

┌────────────────────────────────────────────────────────────────────────┐
│                          AI Clients & Agents                           │
│  ┌────────────────┐  ┌──────────────┐  ┌───────────┐  ┌──────────────┐ │
│  │ Claude Desktop │  │  Cursor IDE  │  │ Windsurf  │  │ In-Browser   │ │
│  │ (Desktop MCP)  │  │ (Agent IDE)  │  │ (Agent)   │  │ (WebMCP W3C) │ │
│  └───────┬────────┘  └──────┬───────┘  └─────┬─────┘  └──────┬───────┘ │
└──────────┼──────────────────┼────────────────┼───────────────┼─────────┘
           │                  │                │               │
           ▼                  ▼                ▼               ▼
┌────────────────────────────────────────────────────────────────────────┐
│                        SkillsMCP Bridge Server                         │
│                                                                        │
│  ┌─────────────────────────┐            ┌────────────────────────────┐ │
│  │   MCP Server Engine     │            │       WebMCP Engine        │ │
│  │ (JSON-RPC 2.0 / SSE)    │            │ (W3C Draft JS Polyfill)    │ │
│  └───────────┬─────────────┘            └─────────────┬──────────────┘ │
│              │                                        │                │
│              ▼                                        ▼                │
│  ┌──────────────────────────────────────────────────────────────────┐  │
│  │              Progressive Disclosure & Token Manager              │  │
│  │     [Dynamic Meta Tool]  •  [Category Slice]  •  [Full Grid]     │  │
│  └──────────────────────────────────┬───────────────────────────────┘  │
│                                     │                                  │
│                                     ▼                                  │
│  ┌──────────────────────────────────────────────────────────────────┐  │
│  │                    Skills & Tools Registry                       │  │
│  │  1,000+ Developer Skills: Architecture, TypeScript, Git, AI/LLMs │  │
│  └──────────────────────────────────┬───────────────────────────────┘  │
│                                     │                                  │
│                                     ▼                                  │
│  ┌──────────────────────────────────────────────────────────────────┐  │
│  │             Automated 24h Background Synchronizer                │  │
│  └──────────────────────────────────────────────────────────────────┘  │
└────────────────────────────────────────────────────────────────────────┘

🚀 Quick Start

Prerequisites

Node.js >= 18.0.0
npm >= 9.0.0

1. Installation

# Clone repository
git clone https://github.com/your-username/skills-mcp-hub.git
cd skills-mcp-hub

# Install dependencies
npm install

2. Environment Setup

Copy .env.example to .env:

cp .env.example .env

Variable	Description	Default
`PORT`	Web and MCP server port	`3000`
`NODE_ENV`	Environment mode (`development` / `production`)	`development`
`APP_URL`	Optional public domain override for SSE links	Auto-detected
`GEMINI_API_KEY`	Optional API key for extended AI execution	`none`

3. Running Locally

# Start development server (Express + Vite with hot reload)
npm run dev

Open http://localhost:3000 in your browser.

🛠️ MCP Client Configuration

1. Claude Desktop

Add this to your claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%\Claude\claude_desktop_config.json):

{
  "mcpServers": {
    "skills-mcp-hub": {
      "command": "npx",
      "args": ["-y", "mcp-remote-client", "http://localhost:3000/api/mcp/sse"]
    }
  }
}

2. Cursor IDE / Windsurf

In Settings → Features → MCP Servers → Add New MCP Server:

Name: skills-mcp-hub
Type: sse
URL: http://localhost:3000/api/mcp/sse

🌐 WebMCP (W3C Web ML CG Protocol)

The platform automatically injects the WebMCP polyfill at /api/webmcp/script. In-browser AI extensions and agents can discover and execute tools using standard JavaScript:

// Check registered tools
const tools = await window.navigator.modelContext.getTools();
console.log(`Discovered ${tools.length} WebMCP tools`);

// Execute an active tool
const result = await window.navigator.modelContext.invoke("webmcp_search_skills_dom", {
  keyword: "TypeScript"
});
console.log(result);

📦 Production Build & Deployment

Build Command

npm run build

This compiles the Vite frontend into dist/ and bundles the standalone backend server into dist/server.cjs.

Production Start

npm start

Free Deployment Options

1. Render (Zero-Config Web Service)

Runtime: Node.js
Build Command: npm run build
Start Command: npm start

2. Google Cloud Run / Docker

A standard Dockerfile can be used:

FROM node:20-alpine
WORKDIR /app
COPY package*.json ./
RUN npm install
COPY . .
RUN npm run build
EXPOSE 3000
CMD ["npm", "start"]

📡 REST & MCP Endpoints

Method	Endpoint	Description
`GET`	`/api/mcp/sse`	MCP Server-Sent Events stream connection
`POST`	`/api/mcp/message`	MCP JSON-RPC 2.0 message handler
`GET`	`/api/skills`	List all indexed agent skills (paginated)
`GET`	`/api/skills/categories`	Get category breakdown & metrics
`POST`	`/api/skills/toggle`	Enable or disable individual skills
`GET`	`/api/mcp/configs`	Generate client config JSON for IDEs
`GET`	`/api/webmcp/tools`	WebMCP in-browser tool discovery list
`POST`	`/api/webmcp/invoke`	WebMCP tool execution handler
`GET`	`/api/sync-engine/status`	Background synchronizer health and schedule metrics

📄 License

This project is released under the MIT License.

This server cannot be installed

license - not tested

Not graded

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

–Release cycle

–Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

SkillDB
A registry of 5,900+ peer-authored skills any MCP agent can search and load on demand.
ToolAPI
Free public MCP for AI agents — 193 tools, 44 workflows. No API key.
mcp-knowledge
100+ MCP tools for AI agents: content metadata, trade intelligence, business-expertise analysis.

View all MCP Connectors

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/AbinashBalaraman/skills-webmcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server