MCP Server

What is MCP?

The Model Context Protocol (MCP) is a standard protocol that allows AI assistants to access external tools and resources. The Loly MCP server provides your AI assistant with:

• Access to complete Loly Framework documentation
• Code examples for common patterns
• API reference information
• Code generation and validation tools

Installation

The Loly MCP server is available at:

https://loly-framework.onrender.com/api/mcp

The MCP server is hosted and ready to use. Simply configure your AI assistant with the URL above.

Setting up in Cursor

To use the Loly MCP server in Cursor:

1. Open Cursor Settings
2. Navigate to Features → Model Context Protocol
3. Click "Add Server"
4. Enter the following configuration:

{
  "mcpServers": {
    "loly": {
      "url": "https://loly-framework.onrender.com/api/mcp",
      "headers": {
        "Content-Type": "application/json"
      }
    }
  }
}

Replace https://loly-framework.onrender.com with your actual server URL. For remote HTTP servers, use the url configuration directly.

Automatic Setup with AI Assistant

You can ask your AI assistant (Cursor, Windsurf, or any MCP-compatible assistant) to automatically configure the Loly MCP server for you. Simply copy and paste the following prompt:

Please configure the Loly Framework MCP server in my Cursor/Windsurf configuration.

MCP Server Details:
- Server Name: loly
- Server URL: https://loly-framework.onrender.com/api/mcp
- Transport: HTTP (remote server)

Configuration to add to mcp.json:
{
  "mcpServers": {
    "loly": {
      "url": "https://loly-framework.onrender.com/api/mcp",
      "headers": {
        "Content-Type": "application/json"
      }
    }
  }
}

Instructions:
1. Locate or create the MCP configuration file (usually at ~/.cursor/mcp.json or in your Cursor/Windsurf settings)
2. Add the "loly" server configuration to the "mcpServers" object
3. If the file already has other MCP servers, merge this configuration with the existing ones
4. Ensure the JSON is valid and properly formatted
5. Save the file and restart Cursor/Windsurf for the changes to take effect

The MCP server provides access to:
- Loly Framework documentation search
- Code examples and patterns
- API reference information
- Code generation and validation tools

Setting up in Windsurf

To use the Loly MCP server in Windsurf:

1. Open Windsurf Settings
2. Navigate to Extensions → MCP Servers
3. Click "Add Server"
4. Enter the following configuration:

{
  "mcpServers": {
    "loly": {
      "url": "https://loly-framework.onrender.com/api/mcp",
      "headers": {
        "Content-Type": "application/json"
      }
    }
  }
}

Available Tools

The Loly MCP server provides the following tools:

{
  "name": "search_loly_docs",
  "arguments": {
    "query": "API routes"
  }
}

{
  "name": "get_loly_example",
  "arguments": {
    "category": "routing",
    "topic": "dynamic"
  }
}

{
  "name": "generate_loly_code",
  "arguments": {
    "description": "Create a page that displays a list of posts",
    "type": "page"
  }
}

{
  "name": "get_loly_api_reference",
  "arguments": {
    "api": "ApiContext"
  }
}

{
  "name": "validate_loly_code",
  "arguments": {
    "code": "export async function GET(ctx: ApiContext) { return ctx.Response({}); }"
  }
}

Available Resources

The following documentation resources are available:

• loly://docs/getting-started
• loly://docs/routing
• loly://docs/api-routes
• loly://docs/websockets
• loly://docs/rendering
• loly://docs/middlewares
• loly://docs/security
• loly://docs/configuration
• loly://docs/api-reference

Usage Examples

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "initialize",
  "params": {
    "protocolVersion": "2024-11-05",
    "capabilities": {},
    "clientInfo": {
      "name": "cursor",
      "version": "1.0.0"
    }
  }
}

{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/list"
}

{
  "jsonrpc": "2.0",
  "id": 3,
  "method": "tools/call",
  "params": {
    "name": "search_loly_docs",
    "arguments": {
      "query": "API routes"
    }
  }
}

{
  "jsonrpc": "2.0",
  "id": 4,
  "method": "resources/read",
  "params": {
    "uri": "loly://docs/getting-started"
  }
}

Troubleshooting