MCP Server

What is MCP?

MCP (Model Context Protocol) is a standardized protocol that enables AI assistants to access external data sources and tools. Movk Nuxt provides an MCP server so AI tools can directly access component information, API documentation and usage examples.

Available Resources

The MCP server provides the following resources for AI discovery and browsing:

Use @ in tools like Claude Code to access these resources.

Available Tools

List Queries

Detail Retrieval

Search & Filter

Available Prompts

The MCP server provides guided prompts for common workflows:

Use / in tools like Claude Code to access these prompts.

Configuration

The Movk Nuxt MCP server uses HTTP transport and can be configured in different AI assistants.

ChatGPT

Configure Movk Nuxt as a ChatGPT connector:

1. Enable developer mode: go to "Settings" > "Connectors" > "Advanced settings" > "Developer mode"
2. Open ChatGPT Settings
3. Create a new connector in the Connectors tab:
   • Name: Movk Nuxt
   • MCP server URL: https://nuxt.mhaibaraai.cn/mcp
   • Authentication: None
4. Click Create

In subsequent conversations, you can invoke the connector from the "Developer mode" tools list in the editor.

Claude Code

Add the server via CLI:

claude mcp add --transport http movk-nuxt https://nuxt.mhaibaraai.cn/mcp

Claude Desktop

1. Open Claude Desktop and go to "Settings" > "Developer"
2. Click "Edit Config" to open the local Claude configuration directory
3. Edit claude_desktop_config.json:

{
  "mcpServers": {
    "movk-nuxt": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://nuxt.mhaibaraai.cn/mcp"
      ]
    }
  }
}

4. Restart Claude Desktop — the Movk Nuxt MCP server will be registered

Cursor

One-Click Install

Click the button below to install the Movk Nuxt MCP server directly in Cursor:

Manual Configuration

1. Open Cursor and go to "Settings" > "Tools & MCP"
2. Add the Movk Nuxt MCP server configuration

Or create/edit .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "movk-nuxt": {
      "type": "http",
      "url": "https://nuxt.mhaibaraai.cn/mcp"
    }
  }
}

Google Antigravity

1. Open the MCP store from the "..." dropdown in the Agent panel at the top of the editor
2. Click "Manage MCP Servers"
3. Click "View raw config"
4. Edit mcp_config.json:

{
  "mcpServers": {
    "movk-nuxt": {
      "serverUrl": "https://nuxt.mhaibaraai.cn/mcp"
    }
  }
}

5. Return to "Manage MCP Servers" and click "Refresh" — the Movk Nuxt MCP server will appear in the list

Gemini CLI

1. Locate the Gemini CLI configuration file (usually at ~/.gemini/settings.json or the path specified by an environment variable)
2. Append the configuration to the mcpServers object:

{
  "mcpServers": {
    "movk-nuxt": {
      "url": "https://nuxt.mhaibaraai.cn/mcp"
    }
  }
}

3. Restart the terminal or reload the CLI — Movk Nuxt MCP tools are now available

Le Chat Mistral

1. Go to "Intelligence" > "Connectors"
2. Click "Add Connector" and select "Custom MCP Connector"
3. Create a custom MCP connector:
   • Connector Name: MovkNuxt
   • Connector Server: https://nuxt.mhaibaraai.cn/mcp

Visual Studio Code

1. Open the VS Code Command Palette (Ctrl/Cmd + Shift + P)
2. Type "Preferences: Open Workspace Settings (JSON)" and execute
3. Create or edit mcp.json in your project's .vscode directory:

{
  "servers": {
    "movk-nuxt": {
      "type": "http",
      "url": "https://nuxt.mhaibaraai.cn/mcp"
    }
  }
}

Windsurf

1. Go to "Settings" > "Windsurf Settings" > "Cascade"
2. Click "Manage MCPs" > "View raw config"
3. Add the following configuration:

{
  "mcpServers": {
    "movk-nuxt": {
      "type": "http",
      "url": "https://nuxt.mhaibaraai.cn/mcp"
    }
  }
}

Zed

1. Go to "Settings" > "Open Settings"
2. Open the JSON settings file
3. Add the context server configuration:

{
  "context_servers": {
    "movk-nuxt": {
      "source": "custom",
      "command": "npx",
      "args": ["mcp-remote", "https://nuxt.mhaibaraai.cn/mcp"],
      "env": {}
    }
  }
}

Opencode

1. Create opencode.json in your project root
2. Add the following configuration:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "movk-nuxt": {
      "type": "remote",
      "url": "https://nuxt.mhaibaraai.cn/mcp",
      "enabled": true
    }
  }
}

GitHub Copilot Agent

If you have already completed configuration in VS Code, you can adapt the same structure (replacing the servers key with mcpServers) and explicitly declare tools to list available tools.

1. Open your GitHub repository
2. Go to "Settings" > "Code & automation" > "Copilot" > "Coding agent"
3. Add the following under "MCP configuration":

{
  "mcpServers": {
    "movk-nuxt": {
      "type": "http",
      "url": "https://nuxt.mhaibaraai.cn/mcp",
      "tools": ["*"]
    }
  }
}

4. Click Save

For more information see Extend coding agent with MCP.

Usage Examples

Once configured, you can ask AI assistants questions across Movk Nuxt's four capability domains:

AutoForm (Schema-Driven Forms)

• "How do I automatically generate a form from a Zod schema?"
• "What field types are supported? How do I register custom controls?"
• "How do I implement conditional field rendering and cross-field dependencies?"
• "I want to build a user registration form — how should I organize the schema?"

DataTable (Data Table)

• "What fields does a DataTable column definition have? How do I use a functional column?"
• "How do I implement tree data, column pinning and column resizing?"
• "How do I configure pagination, load-more and empty states?"
• "I need an editable table with a row right-click menu — which APIs should I use?"

API System (Fetch & Progress)

• "What is the difference between useApiFetch and $fetch?"
• "How do I configure multiple endpoints and automatic auth?"
• "How do I monitor file upload/download progress?"
• "How do I integrate business status codes and Toast notifications?"

Standalone Components & Composables

• "What standalone UI components are available?"
• "What props do DatePicker, StarRating and PillGroup accept?"
• "How do I use useDateFormatter, useTheme and useMessageBox?"
• "I need a date range picker — which component is recommended?"

AI assistants retrieve structured data via MCP tools and provide contextual suggestions; questions with "recommend / what should I use" automatically trigger guided prompts.