Provides access to Laravel-specific documentation, coding rules, CRUD templates, and validation checklists to assist in Laravel application development and architectural decision-making.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Laravel AI MCP Server search the docs for database transactions and show me the CRUD templates"
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.
MCP (Model Context Protocol) server for providing Laravel AI documentation to Claude Code and other AI assistants.
# Clone or navigate to the project directory
cd laravel-ai
npm installnpm startDocumentation is expected to be in: ./docs (relative to project root)
Related MCP server: directory-indexer
Add to your Claude Code settings (~/.config/claude-code/config.json):
{
"mcpServers": {
"laravel-ai": {
"command": "node",
"args": ["path/to/laravel-ai/index.js"]
}
}
}If your documentation is in a different location:
{
"mcpServers": {
"laravel-ai": {
"command": "node",
"args": ["path/to/laravel-ai/index.js"],
"env": {
"DOCS_PATH": "/path/to/your/docs"
}
}
}
}Tool | Description |
| Get all documentation files structure |
| Read a specific documentation file |
| Search across all documentation |
| Get all coding rules (quick-reference.md) |
| Get CRUD templates (specific or all) |
| Get validation checklist (specific layer or all) |
| Get domain-specific examples |
| Get design system documentation |
laravel-ai/
├── docs/ # Documentation folder
│ ├── ai/
│ │ ├── quick-reference.md # All coding rules
│ │ ├── templates.md # Implementation templates
│ │ └── checklist.md # Validation checklist
│ ├── domains/
│ │ ├── ecommerce/ # E-commerce examples
│ │ ├── hr/ # HR examples
│ │ └── tourism/ # Tourism examples
│ ├── patterns/ # Pattern documentation
│ └── design-system.md # Design system (configurable)
├── index.js # MCP server
├── package.json # Dependencies
└── README.md # This fileWhen user says "pelajari docs", AI should:
// 1. Get quick reference
mcp.call_tool('get_quick_reference')
// 2. Get templates
mcp.call_tool('get_templates', { template_type: 'all' })
// 3. Get checklist
mcp.call_tool('get_checklist', { layer: 'all' })
// 4. Confirm ready// Search for "transaction"
mcp.call_tool('search_docs', { query: 'transaction' })// Get e-commerce examples
mcp.call_tool('get_domain_examples', { domain: 'ecommerce' })
// Get all domains overview
mcp.call_tool('get_domain_examples', { domain: 'all' })npm run devTest the MCP server manually:
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | node index.jsThis server uses stdio transport for communication
All documentation is read from the file system
No caching - always reads latest documentation
Supports incremental updates to documentation
When documentation is updated, just restart the MCP server:
# Stop current server (Ctrl+C)
npm startVersion: 1.0.0 Last Updated: 2026-02-23
Get code validation checklist
Inputs: layer.
Get design system documentation
Inputs: no named parameters.
Get the structure of all available documentation files
Inputs: no named parameters.
Get domain-specific implementation examples
Inputs: domain.
Get the quick reference documentation (all coding rules)
Inputs: no named parameters.
Get implementation templates for CRUD operations
Inputs: template_type.
Read a specific documentation file
Inputs: file_path (required).
Search for content across all documentation files
Inputs: query (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 8 tools
Every tool has a clearly distinct purpose with no ambiguity. The tools target different aspects of documentation retrieval: checklists, design systems, structures, examples, references, templates, specific files, and search. There is no overlap in functionality.
All tools follow a consistent verb_noun pattern using snake_case. Each name starts with 'get_' or a similar verb ('read_', 'search_') followed by a descriptive noun, making the set predictable and readable.
With 8 tools, the server is well-scoped for its purpose of providing Laravel documentation and resources. Each tool earns its place by covering a specific aspect of documentation retrieval, avoiding bloat or thinness.
The tool surface is complete for the domain of documentation access, covering all key operations: retrieving specific files, searching, getting structured overviews, examples, templates, and references. There are no obvious gaps that would hinder an agent's workflow.
Provide your AI coding tools with token-efficient access to up-to-date technical documentation for…
Versioned documentation registry and semantic search for AI tools and coding assistants.
Serves your design system and coding standards to coding agents, so they stop guessing.
Project memory, documentation and controlled secret access for AI coding agents.
