MCP Tools
MCP Tools is a module that provides AI assistant tools for Drupal sites. It includes 223 tools, supports read - write operations, resource access, and prompt functions. It is mainly used for local development and prototyping, with a modular architecture and a three - layer access control security mechanism.
2.5 points
6.7K

What is MCP Tools?

MCP Tools is an AI assistant toolkit designed for Drupal websites. It allows AI assistants (such as Claude, ChatGPT, etc.) to interact with Drupal sites through natural language and perform various operations, from simple content queries to complex site building tasks. Imagine that you can tell the AI assistant: 'Create a blog system that includes articles, categories, tags, and editor roles', and the AI will automatically create content types, fields, category vocabularies, user roles, and permissions for you.

How to use MCP Tools?

Using MCP Tools is very simple: 1. Install the MCP Tools module on your Drupal site. 2. Select a connection method (the local STDIO method is recommended). 3. Configure your AI assistant to connect to the MCP server. 4. Start interacting with your Drupal site through natural language. MCP Tools provides two main connection methods: the local STDIO method (recommended for development) and the remote HTTP method (for test environments).

Applicable scenarios

MCP Tools is most suitable for the following scenarios: • Local development environment: Rapid prototyping and site building. • Content management: Batch creation, update, and deletion of content. • Site configuration: Management of users, roles, permissions, and menus. • Automation tasks: Execution of repetitive management operations. • Learning and teaching: Understanding various functions of Drupal. Note: It is recommended to use read-only mode in the production environment to ensure site security.

Main features

Complete site building capabilities
Supports the creation of a complete site structure including content types, fields, category vocabularies, user roles, permissions, views, blocks, etc. The AI assistant can build complex Drupal sites through natural language descriptions.
Modular architecture
Adopts a modular design. 35 sub - modules provide 198 write - operation tools and 25 read - only tools. You can enable specific functional modules as needed to keep the system lightweight.
Multi - layer security control
Provides three - layer access control: module level, global read - only mode, and connection scope. Built - in protection mechanisms prevent dangerous operations, such as protecting user ID 1 and the administrator role.
Multiple connection methods
Supports the local STDIO method (recommended) and the remote HTTP method. The STDIO method runs through Drush commands, and the HTTP method provides API key authentication.
Resources and prompts
Provides read - only resources (such as site status and configuration snapshots) and reusable analysis prompts to help the AI assistant better understand the site context.
Observability hooks
All tool executions trigger events, supporting custom log recording, metric collection, or Webhook notifications for easy monitoring and auditing.
Advantages
Significantly improve development efficiency: Quickly complete complex Drupal configuration tasks through natural language.
Reduce the learning curve: Non - technical personnel can also manage Drupal sites through AI assistants.
Modular design: Enable functions as needed to keep the system lightweight.
Enterprise - level security: Multi - layer access control and built - in protection mechanisms.
Flexible deployment: Supports local and remote connection methods.
Complete coverage: 223 tools cover core Drupal functions.
Limitations
Production environment risks: Write operations may cause configuration drift. It is recommended to use read - only mode.
Dependence on AI assistants: Requires an AI assistant that supports the MCP protocol.
Learning cost: Requires an understanding of the MCP protocol and basic Drupal concepts.
Performance considerations: Complex operations may take a long time.
Version limitations: Only supports Drupal 10.3+ and Drupal 11.

How to use

Install MCP Tools
Install and enable the MCP Tools module via Composer.
Select a connection method
Select a connection method according to your usage scenario. The STDIO method is recommended for local development.
Start the MCP server
Start the MCP server using the Drush command. It is recommended to use uid = 1 for local development.
Configure the AI assistant
Configure the MCP server connection in your AI assistant (such as Claude Desktop).
Enable required functional modules
Enable specific functional modules as needed. You can start with the core site building modules.

Usage examples

Create a blog system
Create a complete blog system through natural language instructions, including content types, categories, user roles, and permissions.
Batch content management
Batch create, update, or delete content to improve content management efficiency.
Site health check
Check the health status of the Drupal site, including security updates, performance issues, and error logs.
User permission management
Manage user roles and permissions to ensure site security.

Frequently Asked Questions

Is MCP Tools secure? Can it be used in a production environment?
Which Drupal versions are supported?
How to control the access permissions of the AI assistant?
Will MCP Tools affect site performance?
How to back up the configurations created by MCP Tools?
Which AI assistants are supported?

Related resources

Official documentation
The GitHub repository for MCP Tools, containing complete documentation, installation guides, and examples.
Drupal project page
The official project page on Drupal.org, containing release versions and issue tracking.
Quick start guide
A 5 - minute quick start guide, suitable for new users.
Troubleshooting
Solutions to common problems and error fixes.
Client integration guide
How to configure various AI clients to connect to MCP Tools.
Usage cases
Examples of actual workflows and best practices.
MCP protocol specification
The official specification document for the Model Context Protocol.
Drupal community support
Join the Drupal Slack community for help and support.

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
4.5K
4.5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
5.7K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
7.3K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
6.6K
5 points
R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
9.4K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
10.8K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
6.5K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
11.5K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
24.4K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.4K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
34.3K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
71.9K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
31.1K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.4K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
21.0K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
48.6K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase