What are the requirements?
PHP 8.1 or higher, Composer, and the `php-mcp/server ^2.1` package.
@VoDmAl
基本情報
概要はまだありません
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
A PHP library that exposes your project’s Composer scripts as MCP (Model Context Protocol) tools. It works with any PHP project and allows you to connect multiple projects without limits, letting AI assistants discover and execute scripts automatically.
Install via composer require vodmal/composer-scripts-mcp-server then composer install. Two scripts are added: mcp:server:start and mcp:server:install. Run composer mcp:server:install for automatic integration with MCP clients (e.g., Claude Desktop). Alternatively, start the server manually with vendor/bin/mcp-server-start (stdio) or with --http flag.
composer.jsoncheck:before:commit) via natural language requestsPHP 8.1 or higher, Composer, and the `php-mcp/server ^2.1` package.
You can install the server in each PHP project folder. Each project’s tool name is derived from its `composer.json` name field, so they appear distinctly in the MCP client.
The server supports stdio transport (default for LLM integration) and HTTP transport (for testing, with optional `--host` and `--port` arguments).
Configuration is merged into the Claude Desktop config file (or printed as JSON if not found). No external data storage is used.
Complex script chains can be harder to debug, and performance may be slightly slower than native binaries. Log messages are written to stderr when using stdio to avoid interfering with JSON communication.

Model Context Protocol Servers

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
🚀 The fast, Pythonic way to build MCP servers and clients.
Hindsight: Agent Memory That Learns
コメント