New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

MCP Development

by cachethq in cachethq/core

A skill your agent uses for Cachet's Laravel MCP server. An agent skill from cachethq/core.

MITAuto-check passedBackend & APIs

Install MCP Development

skills CLI
$ npx skills add cachethq/core --skill mcp-development -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cachethq/core mcp-development --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cachethq/core.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/mcp-development .claude/skills/mcp-development && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
mcp-development
GitHub stars
230
Token cost
~1.4k tokens
SKILL.md length
366 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses for Cachet's Laravel MCP server. An agent skill from cachethq/core.

  • Cachets Laravel MCP server
  • SKILL.md covers Documentation First, Core Package Conventions, Quick Reference and Testing MCP Primitives, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Editing MCP tools

What it does

MCP Development is an agent skill from cachethq/core. Use this skill for Cachet's Laravel MCP server. Trigger when creating or editing MCP tools, resources, prompts, server registration, schemas, annotations, authentication, authorization, visibility, or MCP tests. Do not use for non-Laravel MCP projects or generic AI features without MCP.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering MCP servers and Backend development. It works with Model Context Protocol, Laravel and PHP. The repository describes itself as: 🚦 The core for Cachet, an open source, self-hosted status page system. The licence is MIT.

When your agent uses it

  • Cachets Laravel MCP server
  • Editing MCP tools
  • Server registration
  • Non-Laravel MCP projects

Example prompts

  • “/mcp-development”

What it can do on your machine

Read from SKILL.md and the folder at commit 57b44a8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are php and bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

MCP Development loads about 1.4k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 366 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~76
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cachethq/core at commit 57b44a8, republished under its MIT licence (© cachethq). 366 words, ~1,400 tokens.

Download SKILL.mdSave it as .claude/skills/mcp-development/SKILL.md (or your agent's skills folder).
name
mcp-development
description
Use this skill for Cachet's Laravel MCP server. Trigger when creating or editing MCP tools, resources, prompts, server registration, schemas, annotations, authentication, authorization, visibility, or MCP tests. Do not use for non-Laravel MCP projects or generic AI features without MCP.
license
MIT
metadata.author
laravel

MCP Development

Documentation First

CRITICAL: Always use search-docs BEFORE writing MCP code. The documentation is version-specific, comprehensive, and always up-to-date.

bash
# Example searches
search-docs(['mcp tools', 'mcp resources', 'mcp validation'])

Core Package Conventions

  • Keep the server and primitives under src/Mcp in the Cachet\\Mcp namespace.
  • Register the web server through CachetCoreServiceProvider; do not create routes/ai.php or modify a host application.
  • Do not use make:mcp-* generators for final code. They target Testbench's host skeleton. Follow sibling tools and create the package file in src/Mcp.
  • Keep server availability, authentication, rate limiting, token abilities, and record visibility aligned with config/cachet.php, the MCP middleware, and existing concerns.
  • Every write tool must guard the matching Sanctum ability in both handle() and shouldRegister().
  • Use the Laravel MCP annotation matching the side effect, including #[IsReadOnly], #[IsIdempotent], and #[IsDestructive] where applicable.
  • Put feature coverage under tests/Feature/Mcp and architecture coverage under tests/Architecture/McpTest.php.

Quick Reference

Package Layout

Inspect the closest tool and its feature test before adding a primitive. Reuse GuardsMcpAbilities, PresentsResources, visibility scopes, pagination, and domain actions instead of duplicating those mechanics.

Basic Tool Implementation
php
use Illuminate\Contracts\JsonSchema\JsonSchema;
use Laravel\Mcp\Request;
use Laravel\Mcp\Response;
use Laravel\Mcp\Server\Tool;

class MyTool extends Tool
{
    protected string $description = 'Tool description for LLM';

    public function schema(JsonSchema $schema): array
    {
        return [
            'param' => $schema->string()->required(),
        ];
    }

    public function handle(Request $request): Response
    {
        return Response::text($request->get('param'));
    }
}
Basic Resource Implementation
php
use Laravel\Mcp\Response;
use Laravel\Mcp\Server\Resource;

class MyResource extends Resource
{
    protected string $description = 'Resource description';
    protected string $uri = 'file://path/to/resource';
    protected string $mimeType = 'text/markdown';

    public function handle(): Response
    {
        return Response::text($content);
    }
}
Response Methods
php
Response::text('Text content');
Response::error('Error message');
Response::structured(['key' => 'value']);

Testing MCP Primitives

Test tools, resources, and prompts directly on their server:

php
// Test a tool
$response = CachetServer::tool(MyTool::class, ['param' => 'value']);
$response->assertOk()->assertSee('Expected text');

// Test as an authenticated user with the matching token ability
Sanctum::actingAs($user, ['resource.manage']);
$response = CachetServer::tool(MyTool::class, [...]);

// Available assertions
$response->assertOk();
$response->assertSee('text');
$response->assertHasErrors();
$response->assertHasNoErrors();
$response->assertName('tool-name');
$response->assertSentNotification('event/type', ['data' => 'value']);

For write tools, also assert the database change, side effects, missing ability, and whether the tool is hidden from callers without that ability. Test status-page visibility whenever the tool reads a scoped record.

Show full SKILL.md (151 more words)Show less
MCP Inspector

Test interactively using the inspector:

bash
vendor/bin/testbench route:list --name=cachet.mcp
vendor/bin/testbench mcp:inspector mcp

The inspector is interactive and may install frontend tooling. Run it only when interactive debugging is needed.

Available Features

The following features exist—use search-docs for implementation details:

  • Tools: schema(), validation, annotations (#[IsReadOnly], #[IsDestructive], etc.)
  • Resources: URI templates (HasUriTemplate), Dynamic resources
  • Prompts: Arguments, multi-message responses
  • All primitives: Dependency injection, shouldRegister(), validation
  • Responses: Text, error, structured, streaming, metadata
  • Server registration: Web routes, local routes, OAuth

Critical Imports

php
use Laravel\Mcp\Request;           // NOT Laravel\Mcp\Server\Request
use Laravel\Mcp\Response;          // NOT Laravel\Mcp\Server\Response
use Laravel\Mcp\Server\Tool;
use Laravel\Mcp\Server\Resource;
use Laravel\Mcp\Server\Prompt;
use Illuminate\Contracts\JsonSchema\JsonSchema;

Common Pitfalls

  • Not using search-docs before implementation
  • Wrong imports: Laravel\Mcp\Server\Request (wrong) vs Laravel\Mcp\Request (correct)
  • Forgetting schema() method for tools with parameters
  • Missing required properties: $description, $uri, $mimeType
  • Wrong response pattern: new Response() instead of Response::text()
  • Generating final package code into Testbench's application skeleton
  • Registering a second server in routes/ai.php instead of extending CachetServer
  • Exposing a write tool without the matching Sanctum ability and registration guard
  • Returning records without Cachet's visibility scope
  • Running mcp:start command locally (hangs waiting for stdin)

© cachethq, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/mcp-development of cachethq/core.

Open the folder on GitHubat commit 57b44a8

Compare with similar skills

MCP Development next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

MCP Development compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
MCP Development this skillcachethq/core230—~1.4kAutomated safety check: PassMIT
MCP Developmentcoollabsio/coolify63k1 repos~949Automated safety check: PassMIT
Laravel Plugin Discoveryaffaan-m/ECC274k2 repos~1.6kAutomated safety check: PassMIT
Lerdliberusoftware/real-estate-laravel112—~7.8kAutomated safety check: WarnMIT
Laravel Plugin Discoveryaffaan-m/ECC274k—~953Automated safety check: PassMIT
Infer Conventionsanonaddy/anonaddy4.9k5 repos~3.1kAutomated safety check: PassMIT

Similar skills

  • MCP Development

    coollabsio/coolify

    A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 1 repo~949 tokens
    Frontend & DesignAuto-check passed

  • Laravel Plugin Discovery

    affaan-m/ECC

    Discover and evaluate Laravel packages via LaraPlugins.io MCP.

    274k GitHub starsUsed in 2 repos~1.6k tokens
    Backend & APIsAuto-check passed

  • Lerd

    liberusoftware/real-estate-laravel

    Manage the lerd local PHP development environment via MCP tools: run framework console commands (artisan, bin/console, etc.), manage services, start/stop queue workers, run composer, manage Node.js…

    112 GitHub stars~7.8k tokensUpdated 2 days ago
    Backend & APIsAuto-check: warnings

  • Laravel Plugin Discovery

    affaan-m/ECC

    通过LaraPlugins.io MCP发现和评估Laravel包。当用户想要查找插件、检查包的健康状况或评估Laravel/PHP兼容性时使用。

    274k GitHub stars~953 tokensUpdated 2 days ago
    Backend & APIsAuto-check passed

  • Infer Conventions

    anonaddy/anonaddy

    A skill your agent uses to analyze how a Laravel application is actually written and record its conventions as shared rules.

    4.9k GitHub starsUsed in 5 repos~3.1k tokens
    Backend & APIsAuto-check passed

  • MCP Server

    rrezartprebreza/spring-boot-skills

    A skill your agent uses when exposing Spring Boot 3 application capabilities through Model Context Protocol tools, resources, or prompts.

    296 GitHub starsUsed in 1 repo~1.1k tokens
    Backend & APIsAuto-check passed

More from cachethq/core

  • Psalm Security Analysis

    cachethq/core

    Runs and interprets Psalm security (taint) analysis on a Laravel project.

    230 GitHub stars~4.7k tokensUpdated 2 days ago
    Auto-check passed

  • Tailwindcss Development

    cachethq/core

    A skill your agent uses for Cachet Tailwind CSS and UI styling: Blade utility classes, public status-page components, Filament dashboard theme work, responsive layout, dark mode, spacing…

    230 GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about MCP Development

What does MCP Development do?

A skill your agent uses for Cachet's Laravel MCP server. An agent skill from cachethq/core. MCP Development is an agent skill from cachethq/core. Use this skill for Cachet's Laravel MCP server.

When should I use MCP Development?

MCP Development fits situations like: cachets Laravel MCP server; editing MCP tools; server registration; non-Laravel MCP projects.

How do I install MCP Development in Claude Code?

Run `npx skills add cachethq/core --skill mcp-development -a claude-code`. Or copy the skill folder (.agents/skills/mcp-development in cachethq/core) into .claude/skills/mcp-development in your project. Claude Code loads it when a task matches its description.

How do I install MCP Development in Codex?

Run `npx skills add cachethq/core --skill mcp-development -a codex`. Or copy the skill folder (.agents/skills/mcp-development in cachethq/core) into .agents/skills/mcp-development in your project. Codex loads it when a task matches its description.

Can I use MCP Development in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cachethq/core --skill mcp-development -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcp-development, .gemini/skills/mcp-development, .github/skills/mcp-development and .opencode/skills/mcp-development in your project.

What does MCP Development need to run?

SKILL.md names no scripts, command-line tools or credentials: MCP Development is instructions for the agent only.

Does MCP Development access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is MCP Development safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does MCP Development use?

MCP Development is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does MCP Development use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to MCP Development?

Skills that share tags, products or a category with MCP Development: MCP Development (coollabsio/coolify, 63k stars), Laravel Plugin Discovery (affaan-m/ECC, 274k stars), Lerd (liberusoftware/real-estate-laravel, 112 stars) and Laravel Plugin Discovery (affaan-m/ECC, 274k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains MCP Development?

cachethq (a GitHub organization) maintains it in cachethq/core, which has 230 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 5, 2026.

Source: cachethq/core on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.