LLaraNode
Guide

MCP & AI Integration

Connect AI assistants to your LaraNode application using the Model Context Protocol

MCP & AI Integration

LaraNode comes with built-in support for the Model Context Protocol (MCP). This allows AI assistants like Claude, Cursor, and ChatGPT to interact directly with your LaraNode application.

MCP Server

The documentation site exposes an MCP server at /mcp that AI assistants can connect to. This provides tools for:

  • Listing documentation pages — Discover all available documentation
  • Reading page content — Retrieve specific documentation pages
  • Searching documentation — Find relevant information quickly

Connecting AI Assistants

Cursor

  1. Open Cursor Settings
  2. Navigate to Features → MCP Servers
  3. Add a new MCP server with URL: https://laranode.doitrix.co.ke/mcp

VS Code

  1. Install the MCP extension
  2. Add the server URL: https://laranode.doitrix.co.ke/mcp

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "laranode-docs": {
      "url": "https://laranode.doitrix.co.ke/mcp"
    }
  }
}

LLM Documentation

LaraNode provides LLM-optimized documentation:

Agent Skills

LaraNode includes a comprehensive set of Agent Skills — specialized instructions that help AI assistants work with the framework more effectively. Each skill provides detailed API references, code patterns, and common tasks for a specific package.

Available Skills

The skills are located in the root skills/ directory and cover every LaraNode package:

Skill NamePackagePurpose
laranode-frameworkFramework overview, philosophy, architecture
laranode-core@lara-node/coreIoC container, Application, Service Providers
laranode-db@lara-node/dbEloquent ORM, Models, Migrations, Query Builder
laranode-router@lara-node/routerRouting, Controllers, OpenAPI generation
laranode-auth@lara-node/authJWT auth, password hashing, token encryption
laranode-validator@lara-node/validator50+ validation rules, custom rules
laranode-cache@lara-node/cacheMulti-driver caching, rate limiting
laranode-queue@lara-node/queueJob queue, workers, scheduler
laranode-events@lara-node/eventsEvent dispatcher, listeners, broadcasting
laranode-mail@lara-node/mailMulti-driver email, Mailable classes
laranode-middlewares@lara-node/middlewaresPre-built HTTP middleware
laranode-carbon@lara-node/carbonDate/time manipulation
laranode-console@lara-node/consoleArtisan CLI, 40+ commands
laranode-horizon@lara-node/horizonQueue monitoring dashboard
laranode-telescope@lara-node/telescopeDebug & observability dashboard
laranode-exports@lara-node/exportsPDF, Excel & CSV export utilities
laranode-csv@lara-node/csvCSV generation, parsing, streaming
laranode-excel@lara-node/excelExcel file generation & parsing
laranode-html@lara-node/htmlHTML rendering, templating, sanitization
laranode-pdf@lara-node/pdfPDF generation via Puppeteer
laranode-xml@lara-node/xmlXML building, parsing, serialization
laranode-create-lara-nodecreate-lara-nodeProject scaffolding

Setting Up Skills

To use Agent Skills with your AI assistant, install the skills collection:

npx skills add laranode/lara-node

Or run the skills.sh script directly:

curl -fsSL https://skills.sh/install.sh | bash
skills link skills

After installation, the skills are available at the root skills/ directory.

Skill Structure

Each skill is a directory containing a SKILL.md file:

skills/
├── laranode-framework/SKILL.md      # Root framework skill
├── laranode-core/SKILL.md           # Core package skill
├── laranode-db/SKILL.md             # Database ORM skill
├── laranode-router/SKILL.md         # Routing skill
└── ...                              # One per package

Skills follow the Agent Skills specification with YAML frontmatter (name, description) and markdown body with step-by-step instructions, code examples, and common patterns.

Using Skills in AI Assistants

Skills are automatically loaded when your AI assistant connects to the LaraNode repository through any skills.sh-compatible client. When you ask a question about a specific package, the corresponding skill activates to provide precise, contextual guidance.

For example, asking "How do I set up model relationships?" activates the DB skill, which provides Eloquent relationship patterns. Asking "How do I define routes?" activates the Router skill.