MCP server for WordPress automation and management using browser automation and API integration
Wordpress MCP MCP server exists for a simple reason — assistants are far more useful when they can act on Wordpress MCP directly instead of describing what you should do. MCP server for WordPress automation and management using browser automation and API integration.
A comprehensive MCP server for WordPress automation. TanukiMCP provides powerful AI-driven tools for creating, managing, and customizing WordPress websites through the Model Context Protocol (MCP), compatible with Cursor, Claude, and other MCP-enabled AI tools.
TanukiMCP is a cloud-based automation platform that enables users to perform complex WordPress tasks through a dedicated web application. It leverages the Model Context Protocol (MCP) and integrates directly with the WordPress REST API to provide a seamless automation experience.
Once Wordpress MCP is connected, these are the calls the assistant has available:
GPT — 4.1** (Default): The most capable model for complex WordPress tasks and codingadvanced — Uses the GPT-4.1 modelbasic — Uses the GPT-4.1-mini modelConfiguration — 1. Install and activate the TanukiMCP Dashboard Plugin in your WordPress site 2. Navigate to the TanukiMCP settings page in your WordPress admin 3Authentication — All requests from the dashboard plugin must include: - Authorization: Bearer 3c9a406341969edf38b3d6d0c8f7685c header - Content-Type: application/jsonYou will need 3 environment variables: TANUKIMCP_MASTER_KEY, REQUIRE_API_KEY, OPENAI_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
@smithery/cli on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
Plenty of browser automation servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Wordpress MCP's toolset — GPT, advanced, basic and 2 more — is a fair guide to whether it matches your workflow. It is maintained by AppleJax2; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| GPT | 4.1** (Default): The most capable model for complex WordPress tasks and coding |
| advanced | Uses the GPT-4.1 model |
| basic | Uses the GPT-4.1-mini model |
| Configuration | 1. Install and activate the TanukiMCP Dashboard Plugin in your WordPress site 2. Navigate to the TanukiMCP settings page in your WordPress admin 3. Configure the following settings: - **API Endpoint**: Set to https://wor |
| Authentication | All requests from the dashboard plugin must include: - Authorization: Bearer 3c9a406341969edf38b3d6d0c8f7685c header - Content-Type: application/json header |
{
"mcpServers": {
"tanuki-wordpress": {
"command": "cmd",
"args": [
"/c",
"npx",
"-y",
"@smithery/cli@latest",
"run",
"remote",
"--url",
"https://wordpress-mcp.onrender.com/sse-cursor",
"--key",
"YOUR_API_KEY_HERE"
]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| TANUKIMCP_MASTER_KEY | Credential the server authenticates with. | Yes |
| REQUIRE_API_KEY | Credential the server authenticates with. | Yes |
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.