mcp-client-laravel: Instructions file for Claude Code

CLAUDE.md

mcp-client-laravel CLAUDE.md is an instructions file for Claude Code from RedberryProducts/mcp-client-laravel. It costs 2,011 tokens per session, scanned A, original, MIT.

Project instructions for a Laravel package that connects applications to Model Context Protocol servers. Laravel is a PHP framework, and MCP is a standard way for applications to expose tools and data to AI clients.

In plain words
What is it for?
Understanding the package structure, connecting to MCP servers over HTTP or standard input/output, and running its local quality checks.
Why use it?
They give developers a map of the package, its request flow, supported connection methods, and the commands used to format, analyse, and test it.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is RedberryProducts/mcp-client-laravel's own configuration. It tells Claude Code how to work on mcp-client-laravel itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-client-laravel configures →

Reuse

Borrowing it

Nothing to install: this file belongs to RedberryProducts/mcp-client-laravel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/RedberryProducts/mcp-client-laravel/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/RedberryProducts/mcp-client-laravel

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-client-laravel CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/redberryproducts/mcp-client-laravel/claude-md/github.svg)](https://agentmods.dev/instructions/redberryproducts/mcp-client-laravel/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/redberryproducts/mcp-client-laravel/claude-md"><img src="https://agentmods.dev/badge/instructions/redberryproducts/mcp-client-laravel/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-client-laravel CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/redberryproducts/mcp-client-laravel/claude-md"><img src="https://agentmods.dev/badge/instructions/redberryproducts/mcp-client-laravel/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,011 This file is loaded in full into every session.
When invoked 2,011 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.02011 $0.02011
Opus 5.5 $0.00804 $0.00804
Sonnet 5.5 $0.00402 $0.00402
Haiku 4.5 $0.00201 $0.00201

Measured 2mo ago against content hash c6b88ebb8087, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-client-laravel CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Overview

MCP Client for Laravel (redberry/mcp-client-laravel) is a Laravel-native client for Model Context Protocol (MCP) servers. It speaks JSON-RPC 2.0 over two transports — Streamable HTTP (spec 2025-03-26) and STDIO — and exposes them through a single facade so a Laravel app can list/call tools, read resources, and observe streamed events from any MCP-compliant server defined in config.

Commands

composer test                          # Run Pest tests
composer test-coverage                 # Tests with coverage
composer analyse                       # PHPStan (level 5, src + config)
composer format                        # Laravel Pint
bin/check                              # Pint → PHPStan → Pest in sequence (the local CI gate)
vendor/bin/pest --filter="test name"   # Run a single test
vendor/bin/pest tests/Transporter/     # Run a directory
composer prepare                       # testbench package:discover (after dep changes)

CI runs Pint (fix-php-code-style-issues.yml), PHPStan (phpstan.yml), and Pest (run-tests.yml) on every push.

File Map

src/
  MCPClient.php                        # User-facing client. connect() → tools()/resources()/callTool()/readResource()
  MCPClientServiceProvider.php         # Spatie PackageServiceProvider — config + binding live here only
  Collection.php                       # Lightweight Countable/IteratorAggregate wrapper for tools/resources lists
  Contracts/
    MCPClient.php                      # Public client interface
  Core/
    TransporterFactory.php             # Maps Transporters enum → concrete transporter (the only place that does)
    Transporters/
      Transporter.php                  # Single-method contract: request(string $action, array $params, ?callable $onEvent): array
      HttpTransporter.php              # Streamable HTTP (Guzzle); content-negotiates JSON vs SSE per request
      StdioTransporter.php             # Symfony Process; line-delimited JSON-RPC over stdin/stdout
    Http/
      SseStreamParser.php              # Streaming SSE → JSON-RPC decoder, surfaces every event via $onEvent
    Exceptions/
      TransporterRequestException.php  # Throw this on any transport-level failure
      ServerConfigurationException.php # Throw this on invalid server config
  Enums/Transporters.php               # 'http' | 'stdio'
  Facades/MCPClient.php                # Laravel facade wrapping Redberry\MCPClient\MCPClient
  Commands/MCPClientCommand.php        # Artisan command stub

config/mcp-client.php                  # Server map; published via `vendor:publish --tag=mcp-client-config`
tests/
  Transporter/                         # HTTP/STDIO/factory tests
  Http/SseStreamParserTest.php         # SSE parser tests
  MCPClient/MCPClientTest.php          # Facade-level integration tests
  Helpers/CollectionTest.php           # Collection unit tests
  Datasets/                            # Shared fixtures (e.g. real-shape responses)
  Pest.php, TestCase.php, ArchTest.php # Pest bootstrap, Orchestra base, debug-call arch rule
ROADMAP.md                             # Authoritative list of P0–P6 follow-ups; each item ships as its own PR

Read the full file on GitHub · 129 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 129 lines · 2,011 tokens per session scan A c6b88ebb8087

Subscribe to this mod's changes

mcp-client-laravel CLAUDE.md is an instructions file published in the GitHub repository RedberryProducts/mcp-client-laravel (13 stars, last pushed 12d ago), licensed MIT. It adds 2,011 tokens to every session, about $0.0080 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

mcp-client-laravel CLAUDE.md compared with instructions from other repositories

mcp-client-laravel CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-client-laravel CLAUDE.mdRedberryProducts/mcp-client-laravelInstructions file1312d agoMITA2,011Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode