Phpactor MCP Server
Provides project-wide semantic PHP refactoring tools (find references, rename classes/members, move class, class info) for AI assistants by wrapping Phpactor.
README
Phpactor MCP Server
MCP server that wraps Phpactor to provide project-wide semantic PHP refactoring tools for AI assistants (Claude Code, etc.).
What it does
Exposes 6 tools that require Phpactor's type-aware engine — things a text-based AI cannot reliably do with grep:
| Tool | Description |
|---|---|
phpactor_index_build |
Build/rebuild project index (prerequisite for other tools) |
phpactor_find_references |
Find all semantic references to a class or member |
phpactor_rename_class |
Rename class + update ALL references project-wide |
phpactor_rename_member |
Rename method/property/constant project-wide |
phpactor_move_class |
Move class to new file/namespace + update references |
phpactor_class_info |
Query class info (implements, implementations) |
See docs/spec.md for full specification.
Prerequisites
- Node.js >= 18
- Phpactor installed and available in PATH (or set
PHPACTOR_BINenv var)# Install Phpactor (PHAR) curl -Lo phpactor https://github.com/phpactor/phpactor/releases/latest/download/phpactor.phar chmod +x phpactor mv phpactor ~/.local/bin/ - PHP >= 8.1
- A PHP project with Composer and PSR-4 autoload configured
Yii2 / non-PSR-4 projects
Phpactor requires PSR-4 autoload mappings. For Yii2 projects, add this to composer.json:
{
"autoload": {
"psr-4": {
"common\\": "common/",
"backend\\": "backend/",
"frontend\\": "frontend/",
"console\\": "console/",
"modules\\": "modules/"
}
}
}
Then run composer dump-autoload.
Install
npm install -g @p4it-kft/phpactor-mcp
No build step needed — the package is published prebuilt to npm.
From source (development)
git clone https://github.com/p4it-kft/@p4it-kft/phpactor-mcp
cd @p4it-kft/phpactor-mcp
npm install
npm run build
Configure in Claude Code
Add to ~/.claude/settings.json (or project-level .claude/settings.json):
{
"mcpServers": {
"phpactor": {
"command": "npx",
"args": ["-y", "@p4it-kft/phpactor-mcp"]
}
}
}
Optionally set PHPACTOR_BIN if Phpactor is not in PATH:
{
"mcpServers": {
"phpactor": {
"command": "npx",
"args": ["-y", "@p4it-kft/phpactor-mcp"],
"env": {
"PHPACTOR_BIN": "/path/to/phpactor"
}
}
}
}
Usage
Once configured, the tools are available to Claude. Typical workflow:
- Build the index first — Claude calls
phpactor_index_buildwith your project path - Use tools — find references, rename, move classes as needed
- Rebuild index after significant file changes
Testing
# Run all integration tests (requires tmp/p4it-website test project)
bash test-phpactor.sh
Development
npm run dev # Watch mode — recompiles on changes
npm run build # One-time build
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.