QIT MCP Server
Enables natural language interaction with the QIT CLI for testing WordPress/WooCommerce plugins. Supports running security, e2e, and activation tests, managing test environments, and accessing test results through conversational commands.
README
QIT MCP Server
An MCP (Model Context Protocol) server that wraps the QIT CLI, enabling natural language interaction and agent-based workflows for WordPress/WooCommerce plugin testing.
Features
- Natural Language Testing: Run QIT tests using conversational commands
- Agent Integration: Enable AI agents to run tests as part of automated workflows
- Full CLI Coverage: Access all essential QIT CLI functionality through MCP tools
- Smart CLI Detection: Automatically finds QIT CLI in PATH, local vendor, or custom location
Prerequisites
- Node.js 18+
- QIT CLI installed and accessible
Installation
git clone https://github.com/woocommerce/qit-mcp
cd qit-mcp
npm install
npm run build
Configuration
Claude Code
Add to your Claude Code MCP settings (~/.claude.json):
{
"mcpServers": {
"qit": {
"type": "stdio",
"command": "node",
"args": ["/path/to/qit-mcp/dist/index.js"],
"env": {
"QIT_CLI_PATH": "/path/to/qit-cli/qit"
}
}
}
}
QIT CLI Detection
The MCP server automatically detects QIT CLI in this order:
QIT_CLI_PATHenvironment variableqitin system PATH./vendor/bin/qit(local Composer installation)
Available Tools
Authentication (2 tools)
| Tool | Description |
|---|---|
authenticate |
Connect to WooCommerce.com Partner Developer account |
get_auth_status |
Check current authentication status |
Test Execution (2 tools)
| Tool | Description |
|---|---|
run_test |
Run any test type (security, e2e, phpstan, activation, etc.) |
run_test_group |
Run a predefined test group from qit.json |
Test Results (4 tools)
| Tool | Description |
|---|---|
get_test_result |
Get test result(s) by ID |
list_tests |
List test runs with filters |
get_test_report |
Get detailed test report |
open_test_result |
Open result in browser |
Groups (1 tool)
| Tool | Description |
|---|---|
get_group_status |
Fetch status of a registered test group |
Environment (5 tools)
| Tool | Description |
|---|---|
start_environment |
Start a local test environment |
stop_environment |
Stop a running environment |
list_environments |
List running environments |
exec_in_environment |
Execute command in environment container |
reset_environment |
Reset environment database |
Packages (2 tools)
| Tool | Description |
|---|---|
manage_package |
Manage test packages (publish, download, scaffold, delete, show) |
list_packages |
List available test packages with filtering |
Configuration (1 tool)
| Tool | Description |
|---|---|
manage_config |
Manage backends, partners, and tunneling configuration |
Utilities (5 tools)
| Tool | Description |
|---|---|
list_extensions |
List extensions you can test |
validate_zip |
Validate a plugin ZIP file |
manage_cache |
Manipulate QIT cache |
get_qit_dir |
Get QIT config directory path |
sync_cache |
Re-sync with QIT Manager |
Usage Examples
Natural Language (via Claude Code)
"Run security tests on my-plugin"
→ run_test(type="security", plugin="my-plugin")
"Start a test environment with PHP 8.2"
→ start_environment(php_version="8.2")
"Show me my recent failed tests"
→ list_tests(status="failed")
"What plugins can I test?"
→ list_extensions()
Programmatic Usage
The MCP server communicates via stdio using the Model Context Protocol. See the MCP documentation for integration details.
Development
# Install dependencies
npm install
# Build
npm run build
# Watch mode
npm run dev
# Run tests
npm test
# Lint
npm run lint
License
MIT
Links
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.