Overview
What is VoDmAl Composer Scripts MCP Server?
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.
How to use VoDmAl Composer Scripts MCP Server?
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.
Key features of VoDmAl Composer Scripts MCP Server
- Automatic discovery of all Composer scripts as MCP tools
- One‑step integration with AI assistants like Claude Desktop
- Supports stdio and HTTP transports
- Automatically adds start/install scripts to
composer.json - Works with any PHP project, no project limit
Use cases of VoDmAl Composer Scripts MCP Server
- AI assistants can run tests, linting, and code generation without manual command explanations
- Developers standardize workflows across team members
- Multiple PHP projects appear distinctly as separate tool sets
- Simplify CI-like checks (e.g.,
check:before:commit) via natural language requests
FAQ from VoDmAl Composer Scripts MCP Server
What are the requirements?
PHP 8.1 or higher, Composer, and the php-mcp/server ^2.1 package.
How does it handle multiple projects?
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.
What transports are supported?
The server supports stdio transport (default for LLM integration) and HTTP transport (for testing, with optional --host and --port arguments).
Where does the configuration live?
Configuration is merged into the Claude Desktop config file (or printed as JSON if not found). No external data storage is used.
Are there any known limitations?
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.
