Package Exports

@junis/wordpress-mcp

Readme

WordPress MCP Server

This is a Model Context Protocol (MCP) server for WordPress, allowing you to interact with your WordPress site using natural language via an MCP-compatible client like Claude for Desktop. This server exposes various WordPress data and functionality as MCP tools.

Usage

Claude Desktop

Download and install Claude Desktop.
Open Claude Desktop settings and navigate to the "Developer" tab.
Copy the contents of the claude_desktop_config.json.example file.
Click "Edit Config" to open the claude_desktop_config.json file.
Copy paste the contents of the example file into the config file. Make sure to replace the placeholder values with your actual values for the WordPress site. To generate the application keys, follow this guide - Application Passwords.
Save the configuration.
Restart Claude Desktop.

Features

This server currently provides tools to interact with core WordPress data:

Unified Content Management (8 tools)

Handles ALL content types (posts, pages, custom post types) with a single set of intelligent tools:

list_content: List any content type with filtering and pagination
get_content: Get specific content by ID and type
create_content: Create new content of any type
update_content: Update existing content of any type
delete_content: Delete content of any type
discover_content_types: Find all available content types on your site
find_content_by_url: Smart URL resolver that can find and optionally update content from any WordPress URL
get_content_by_slug: Search by slug across all content types

Unified Taxonomy Management (8 tools)

Handles ALL taxonomies (categories, tags, custom taxonomies) with a single set of tools:

discover_taxonomies: Find all available taxonomies on your site
list_terms: List terms in any taxonomy
get_term: Get specific term by ID
create_term: Create new term in any taxonomy
update_term: Update existing term
delete_term: Delete term from any taxonomy
assign_terms_to_content: Assign terms to any content type
get_content_terms: Get all terms for any content

Specialized Tools

Media:
- list_media: List all media items (supports pagination and searching).
- get_media: Retrieve a specific media item by ID.
- create_media: Create a new media item from a URL.
- update_media: Update an existing media item.
- delete_media: Delete a media item.
Users:
- list_users: List all users with filtering, sorting, and pagination options.
- get_user: Retrieve a specific user by ID.
- create_user: Create a new user.
- update_user: Update an existing user.
- delete_user: Delete a user.
Comments:
- list_comments: List all comments with filtering, sorting, and pagination options.
- get_comment: Retrieve a specific comment by ID.
- create_comment: Create a new comment.
- update_comment: Update an existing comment.
- delete_comment: Delete a comment.
Plugins:
- list_plugins: List all plugins installed on the site.
- get_plugin: Retrieve details about a specific plugin.
- activate_plugin: Activate a plugin.
- deactivate_plugin: Deactivate a plugin.
- create_plugin: Create a new plugin.
Plugin Repository:
search_plugins: Search for plugins in the WordPress.org repository.
get_plugin_info: Get detailed information about a plugin from the repository.
Database Queries:
execute_sql_query: Execute read-only SQL queries against the WordPress database (requires custom endpoint setup).

Key Advantages

Smart URL Resolution

The find_content_by_url tool can:

Take any WordPress URL and automatically find the corresponding content
Detect content types from URL patterns (e.g., /documentation/ → documentation custom post type)
Optionally update the content in a single operation
Works with posts, pages, and any custom post types

Universal Content Operations

All content operations use a single content_type parameter:

{
  "content_type": "post",        // for blog posts
  "content_type": "page",        // for static pages  
  "content_type": "product",     // for WooCommerce products
  "content_type": "documentation" // for custom post types
}

Universal Taxonomy Operations

All taxonomy operations use a single taxonomy parameter:

{
  "taxonomy": "category",        // for categories
  "taxonomy": "post_tag",        // for tags
  "taxonomy": "product_category", // for WooCommerce
  "taxonomy": "skill"            // for custom taxonomies
}

Using with npx and .env file

You can run this MCP server directly using npx without installing it globally:

npx -y @instawp/mcp-wp

Make sure you have a .env file in your current directory with the following variables:

WORDPRESS_API_URL=https://your-wordpress-site.com
WORDPRESS_USERNAME=wp_username
WORDPRESS_PASSWORD=wp_app_password

# Optional: Custom SQL query endpoint (default: /mcp/v1/query)
WORDPRESS_SQL_ENDPOINT=/mcp/v1/query

Enabling SQL Query Tool (Optional)

The execute_sql_query tool allows you to run read-only SQL queries against your WordPress database. This is an optional feature that requires adding a custom REST API endpoint to your WordPress site.

Security Notes:

This tool only accepts read-only queries (SELECT, WITH...SELECT, EXPLAIN) for safety
Queries containing INSERT, UPDATE, DELETE, DROP, or other modifying statements will be rejected
Multi-statement queries are blocked to prevent SQL injection
Queries and results are logged to logs/wordpress-api.log - avoid including sensitive data in queries
This tool requires admin-level permissions (manage_options capability)

Configuration: By default, the tool expects the endpoint at /mcp/v1/query. You can customize this by setting the WORDPRESS_SQL_ENDPOINT environment variable (e.g., WORDPRESS_SQL_ENDPOINT=/custom/v1/query).

To enable this feature, add the following code to your WordPress site (via a custom plugin or your theme's functions.php):

add_action('rest_api_init', function() {
    register_rest_route('mcp/v1', '/query', array(
        'methods' => 'POST',
        'callback' => function($request) {
            global $wpdb;
            
            $query = $request->get_param('query');
            
            // Additional security check
            if (!current_user_can('manage_options')) {
                return new WP_Error('unauthorized', 'Unauthorized', array('status' => 401));
            }
            
            // Only allow SELECT queries
            if (stripos(trim($query), 'SELECT') !== 0) {
                return new WP_Error('invalid_query', 'Only SELECT queries allowed', array('status' => 400));
            }
            
            $results = $wpdb->get_results($query, ARRAY_A);
            
            if ($wpdb->last_error) {
                return new WP_Error('query_error', $wpdb->last_error, array('status' => 400));
            }
            
            return array(
                'results' => $results,
                'num_rows' => count($results)
            );
        },
        'permission_callback' => function() {
            return current_user_can('manage_options');
        }
    ));
});

After adding this code, you can use the execute_sql_query tool to run queries like:

SELECT * FROM wp_posts WHERE post_type = 'post' AND post_status = 'publish' LIMIT 10

Development

Prerequisites

Node.js and npm: Ensure you have Node.js (version 18 or higher) and npm installed.
WordPress Site: You need an active WordPress site with the REST API enabled.
WordPress API Authentication: Set up authentication for the WordPress REST API. This typically requires an authentication plugin or method (like Application Passwords).
MCP Client: You need an application that can communicate with the MCP Server. Currently, Claude Desktop is recommended.

Installation and Setup

Clone the Repository:

git clone <repository_url>
cd wordpress-mcp-server

Install Dependencies:
```
npm install
```
Create a .env file:

Create a .env file in the root of your project directory and add your WordPress API credentials:
```
WORDPRESS_API_URL=https://your-wordpress-site.com
WORDPRESS_USERNAME=wp_username
WORDPRESS_PASSWORD=wp_app_password
```
Replace the placeholders with your actual values.
Build the Server:
```
npm run build
```
Configure Claude Desktop:
- Open Claude Desktop settings and navigate to the "Developer" tab.
- Click "Edit Config" to open the claude_desktop_config.json file.
- Add a new server configuration under the mcpServers section. You will need to provide the absolute path to the build/server.js file and your WordPress environment variables.
- Save the configuration.

Running the Server

Once you've configured Claude Desktop, the server should start automatically whenever Claude Desktop starts.

You can also run the server directly from the command line for testing:

npm start

or in development mode:

npm run dev

Security

Never commit your API keys or secrets to version control.
Use HTTPS for communication between the client and server.
Validate all inputs received from the client to prevent injection attacks.
Implement proper error handling and rate limiting.

Project Overview

Architecture

The server uses a unified tool architecture to reduce complexity:

src/
├── server.ts                    # MCP server entry point
├── wordpress.ts                 # WordPress REST API client
├── cli.ts                      # CLI interface
├── types/
│   └── wordpress-types.ts      # TypeScript definitions
└── tools/
    ├── index.ts                # Tool aggregation
    ├── unified-content.ts      # Universal content management (8 tools)
    ├── unified-taxonomies.ts   # Universal taxonomy management (8 tools)
    ├── media.ts               # Media management (~5 tools)
    ├── users.ts               # User management (~5 tools)
    ├── comments.ts            # Comment management (~5 tools)
    ├── plugins.ts             # Plugin management (~5 tools)
    ├── plugin-repository.ts   # WordPress.org plugin search (~2 tools)
    └── sql-query.ts           # Database queries (1 tool)

Key Features

Smart URL Resolution: Automatically detect content types from URLs and find corresponding content
Universal Content Management: Single set of tools handles posts, pages, and custom post types
Universal Taxonomy Management: Single set of tools handles categories, tags, and custom taxonomies
Token-Optimized Responses: HTML/JSON cleaning reduces token usage by ~84% — SEO metadata, CSS attributes, duplicate image URLs, and non-content HTML tags are stripped automatically
Type Safety: Full TypeScript support with Zod schema validation
Comprehensive Logging: Detailed API request/response logging for debugging
Error Handling: Graceful error handling with informative messages

Response Optimization

All content responses (list_content, get_content, find_content_by_url, get_content_by_slug) are automatically optimized for LLM consumption:

JSON fields removed (confirmed unnecessary for LLM):

yoast_head / yoast_head_json — SEO metadata (~40% of raw payload)
_links — HAL hypermedia links
guid, date_gmt, modified_gmt, ping_status, comment_status, class_list

HTML cleaning (in content and excerpt):

srcset / data-srcset / sizes — duplicate image URLs at multiple sizes removed
class, style, id, data-*, aria-* attributes — CSS/JS noise removed
<script>, <style> blocks — inline code removed
Non-content HTML tags stripped; <img src>, <a href>, <video> preserved
title, content, excerpt flattened from { rendered: "..." } to plain strings
HTML entities decoded to readable text

Result: 24 articles with full body text in ~29.5K tokens (vs ~182K tokens raw)

Content Retrieval Guide

List content with body (single request, no pagination needed for <100 items):

{
  "tool": "list_content",
  "arguments": {
    "content_type": "post",
    "per_page": 30,
    "orderby": "date",
    "order": "desc"
  }
}

Response includes full body text for each item. No need to call get_content individually — body is already included in list responses.

Common content_type values:

post — blog posts
page — static pages
stories, news, press — custom post types (use discover_content_types to find all available types)

Filtering examples:

{ "content_type": "post", "per_page": 10, "search": "skincare", "status": "publish" }
{ "content_type": "post", "per_page": 50, "categories": 5, "orderby": "date", "order": "desc" }
{ "content_type": "page", "per_page": 100, "parent": 0 }

Get single content by ID:

{ "tool": "get_content", "arguments": { "content_type": "post", "id": 21919 } }

Find content by URL (auto-detects content type):

{ "tool": "find_content_by_url", "arguments": { "url": "https://example.com/stories/my-article/" } }

Response shape (per item):

{
  "id": 21919,
  "title": "Article Title (plain text)",
  "content": "Cleaned body text with <img src=\"...\"> and <a href=\"...\">links</a> preserved",
  "excerpt": "Short summary text",
  "slug": "article-slug",
  "date": "2025-11-21T18:16:45",
  "modified": "2025-11-21T18:16:45",
  "link": "https://example.com/stories/article-slug/",
  "status": "publish",
  "type": "stories",
  "author": 1,
  "featured_media": 12345,
  "acf": {}
}

Getting Started

Clone the repository and install dependencies with npm install
Create a .env file with your WordPress credentials
Build the project with npm run build
Configure Claude Desktop with the server
Start using natural language to manage your WordPress site!

Contribution

Feel free to open issues or make pull requests to improve this project. Check out CLAUDE.md for detailed development guidelines.

@junis/wordpress-mcp