Laravel Codebase Introspection
Introspects Laravel codebases to provide structured information about views, routes, classes, and models using the mateffy/laravel-introspect package.
MCP Server for Laravel Codebase Intelligence and Introspection
For AIs to make sense of your codebase, they need to be able to know what's in it. While vector search is a powerful tool for searching through code, it uses a lot of tokens and doesn't even give you the full picture of your codebase for things like views or routes. This package implements a Model Context Protocol (MCP) server for the mateffy/laravel-introspect package, which allows you to introspect your codebase and get structured information about it.
- ๐ Let AI query views, routes, classes and models without needing to read through all of the code
- ๐ Can even use wildcards (
*) to match multiple views, routes, classes and models - ๐ Supports querying for things from Laravel packages, which most file searchers can't do
- ๐ช Gives your AI quick overviews of your datamodel and its relationships
- ๐ค Supports any AI agent implementing the MCP protocol
| Query | Available Filters |
|---|---|
| Views | name, path, used by view, uses view, extends |
| Routes | name, URI, controller + fn, methods, middleware |
| Classes | name / namespace, extends parent, implements interfaces, uses traits |
| โคท Models | ... relationships, properties, casts, fillable, hidden, read/writeable |
| โคท Commands | ... signature, description (coming soon) |
Name and a few other queries even support wildcard queries (e.g.
components.*.paragraph)
Who is this for?
If you use AI tools like Aider, Cursor, Windsurf or Claude Code to help you build your app, this package is for you. Simply configure the MCP server in your agent and it can automatically query your codebase for views, routes, classes and models.
This is especially useful for large codebases where just searching through the code is less practical.
Example tasks
- Give your AI an overview of your datamodel and its relationships
- Refactoring views and making sure it's not used anywhere else
- Finding all routes that use a specific controller
- Finding models that use a specific trait or interface
- Making sure all routes are using the correct middleware
laravel-codebase-mcp vs. laravel-introspect
The MCP server uses the laravel-introspect package to introspect your codebase and get structured information about it.
If you want to write tests or run the same queries multiple times, you can also just use the package directly.
Installation
Install the package via composer:
composer require mateffy/laravel-codebase-mcp --dev
[!NOTE]
At the moment, there is a dependency issue with
php-mcp/server(#23) and ReactPHP (#542). You may temporarily need to use these patched forks if you run into issues when installinglaravel-codebase-mcpby adding the following to yourcomposer.json:{ "repositories": [ { "type": "vcs", "url": "https://github.com/leantime/php-mcp-server.git" }, { "type": "vcs", "url": "https://github.com/Leantime/reactphp-http.git" } ] }
And then add it to your AI agent's MCP configuration:
{
"mcpServers": {
"laravel-introspect": {
"command": "php",
"args": [
"/path/to/your/codebase/artisan",
"introspect:mcp"
]
}
}
}
[!IMPORTANT]
The MCP server is still in beta, there will probably be bugs!
Available queries
If you want to see all available queries, please check the laravel-introspect package documentation.
Acknowledgements
The MCP server uses the php-mcp/server package to implement the MCP protocol.
License
The MIT License (MIT). Please see License File for more information.
Server Terkait
Scout Monitoring MCP
sponsorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Cisco SSH MCP Server
Connect to, configure, and monitor Cisco network devices like routers and switches via SSH.
Luma AI MCP Server
Generate and manipulate AI videos and images using Luma AI's Dream Machine API.
Code Context Provider MCP
Provides code context and analysis for AI assistants using WebAssembly Tree-sitter parsers.
Woodpecker MCP Server
A server for managing Woodpecker CI/CD pipelines, built with the MCP framework.
Stata-MCP
Perform regression analysis using Stata with the help of an LLM. Requires a local Stata installation and an external LLM API key.
Grafana
Access and manage Grafana resources, including dashboards, datasources, Prometheus, Loki, and alerting.
Guardian MCP
Engineering discipline and persistent memory for AI coding assistants
Inoyu Apache Unomi
Maintains user context and manages profiles using the Apache Unomi Customer Data Platform.
MCP JS Debugger
Debug JavaScript and TypeScript applications through the Chrome DevTools Protocol with full source map support.
IDA Pro
Interact with IDA Pro for reverse engineering and binary analysis tasks.