WordPress MCP Python
A lightweight MCP server that connects to WordPress via REST API, enabling content management (posts, pages, categories, etc.) and site configuration through natural language commands.
README
WordPress MCP Python
A lightweight standalone Python MCP server that connects to WordPress via REST API.
Features
- Standalone Python package - Runs independently, no WordPress plugin needed
- Easy setup with
pip install - Full WordPress REST API support: Posts, Pages, Categories, Tags, Users, Media, Settings
- WooCommerce support: Products, Orders (optional)
- MCP SDK integration for Claude Desktop
- Async/await for better performance
Requirements
- Python 3.8+
- WordPress site with REST API enabled
- Application Password or JWT token
Installation
From PyPI (recommended)
pip install wordpress-mcp
From source
git clone https://github.com/tannht/wordpress-mcp-python.git
cd wordpress-mcp-python
pip install -e .
Configuration
1. Get WordPress Application Password
- Go to WordPress Admin → Users → Profile
- Scroll down to Application Passwords
- Create a new one (name it "MCP")
- Copy the generated password
Format: abcd-efgh-ijkl-mnop (4 groups of 4 chars)
2. Set Environment Variables
export WP_URL="https://yoursite.com"
export WP_USERNAME="your_username"
export WP_PASSWORD="your_application_password"
Or use JWT token:
export WP_URL="https://yoursite.com"
export WP_JWT_TOKEN="your_jwt_token"
Usage
As a Library
import asyncio
from wordpress_mcp import WordPressClient
async def main():
client = WordPressClient(
base_url="https://yoursite.com",
username="your_username",
password="your_app_password"
)
# Create a post
post = await client.create_post(
title="Hello from Python!",
content="This post was created via Python MCP.",
status="draft"
)
print(f"Created post: {post['id']}")
asyncio.run(main())
As MCP Server (for Claude Desktop)
# Run the MCP server
python -m wordpress_mcp
Claude Desktop Integration
Add to your Claude Desktop config:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"wordpress": {
"command": "python",
"args": ["-m", "wordpress_mcp"],
"env": {
"WP_URL": "https://yoursite.com",
"WP_USERNAME": "your_username",
"WP_PASSWORD": "your_application_password"
}
}
}
}
Docker
Build and run the MCP server using Docker:
# Build and start the server
docker compose up -d --build
# View logs
docker compose logs -f
# Stop the server
docker compose down
The server runs on stdio transport and connects to WordPress via REST API.
Environment Variables
Create a .env file in the project root:
WP_URL=https://yoursite.com
WP_USERNAME=your_username
WP_PASSWORD=your_application_password
# Or use JWT token
# WP_JWT_TOKEN=your_jwt_token
Claude Code Integration
Add the WordPress MCP server to Claude Code:
claude mcp add --transport stdio wordpress \
--env WP_URL=https://yoursite.com \
--env WP_USERNAME=your_username \
--env WP_PASSWORD=your_application_password \
-- wordpress-mcp
Verify connection:
claude mcp list
MCP Tools Available
Posts
wp_posts_search- Search posts with paginationwp_get_post- Get post by IDwp_add_post- Create new postwp_update_post- Update postwp_delete_post- Delete post
Pages
wp_pages_search- Search pageswp_get_page- Get page by IDwp_add_page- Create new page
Categories
wp_list_categories- List all categorieswp_add_category- Add new category
Tags
wp_list_tags- List all tagswp_add_tag- Add new tag
Users
wp_users_search- Search userswp_get_user- Get user by ID
Media
wp_media_search- Search media items
Settings
wp_get_site_info- Get site informationwp_get_settings- Get site settings
WooCommerce (optional)
wc_products_search- Search productswc_get_product- Get product by IDwc_add_product- Create productwc_orders_search- Search orderswc_get_order- Get order by ID
Development
Setup Development Environment
# Install with dev dependencies
pip install -e ".[dev]"
# Run tests
pytest
# Run tests with coverage
pytest --cov=wordpress_mcp
# Format code
black src/ tests/
# Lint
ruff check src/ tests/
Project Structure
wordpress-mcp-python/
├── pyproject.toml # Project metadata, dependencies
├── README.md
├── .gitignore
├── src/
│ └── wordpress_mcp/
│ ├── __init__.py # Package init, entry point
│ ├── client.py # WordPress REST API client
│ └── server.py # MCP server implementation
├── tests/
│ ├── __init__.py
│ ├── conftest.py # Pytest fixtures
│ └── test_client.py # Client tests
└── scripts/
└── test_connection.py # Connection test script
Troubleshooting
Connection refused
- Make sure WordPress REST API is enabled
- Check your site URL is correct (include https://)
Authentication failed
- Verify Application Password is correct
- Ensure username has proper permissions
Import errors
- Check Python version (3.8+ required)
- Install with
pip install -e .for development
Comparison: Python vs PHP
| Feature | Python MCP | PHP Plugin |
|---|---|---|
| Installation | pip install | Upload plugin |
| Size | ~50KB | ~160KB |
| Dependencies | mcp, httpx, pyjwt | firebase/php-jwt |
| Location | Runs anywhere | Must be in WordPress |
| Update | git pull | Plugin update |
License
MIT
Credits
Based on WordPress MCP by Automattic.
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.