WordPress/mcp-adapter

An MCP adapter that bridges the Abilities API to the Model Context Protocol, enabling MCP clients to discover and invoke WordPress plugin, theme, and core abilities programmatically.

What it solves

It provides a standardized way for AI agents to interact with WordPress functionality. By bridging the WordPress Abilities API with the Model Context Protocol (MCP), it allows AI agents to discover and use WordPress tools, resources, and prompts without needing custom, one-off integrations for every agent.

How it works

The adapter converts WordPress "abilities" into MCP-compliant tools, resources, and prompts. It supports multiple MCP servers and provides two primary transport methods: HTTP and STDIO (via WP-CLI). It uses an opt-in model where abilities are private by default and must be explicitly marked as public to be exposed to AI agents.

Who it’s for

Developers who want to integrate AI agents into WordPress sites or allow external AI clients (like Claude Desktop) to manage and interact with WordPress content and functionality.

Highlights

  • Ability-to-MCP conversion: Automatically turns WordPress abilities into standardized MCP tools, resources, and prompts.
  • Multi-server support: Ability to run multiple MCP servers with independent transports and handlers.
  • Flexible Transports: Supports HTTP and STDIO, with an interface for creating custom protocols.
  • Security: Includes granular permissions, transport authentication, and a per-ability permission check system.

Related

  • Project
    msrbuilds/elementor-mcp

    A WordPress plugin that exposes site functionality as MCP tools, enabling AI agents to build pages, manage content, and operate plugins.

  • Project
    use-novamira/novamira

    An open-source WordPress plugin and MCP server that gives AI agents direct access to execute PHP, run WP-CLI commands, and manage files on a WordPress site.

  • Project
    IBM/mcp

    A collection of Model Context Protocol (MCP) servers and tools that enable AI agents to securely interact with IBM products, enterprise data, and cloud infrastructure.

  • Project
    mattt/emcee

    A tool that converts any web application with an OpenAPI specification into a Model Context Protocol (MCP) server, allowing AI models to use the API as a tool.

  • Project
    hkr04/cpp-mcp

    A C++ implementation of the Model Context Protocol (MCP) that allows AI models and agents to interact with tools, resources, and services through a standardized interface.