storyblok MCP Server

Use This MCP server To

Create Storyblok components using natural language descriptions Update existing Storyblok components with new fields and properties List all available Storyblok components programmatically Generate smart component schemas from descriptive text Manage complex field types like richtext, asset, and multilink in components

README

Storyblok MCP

A Model Context Protocol (MCP) implementation for Storyblok that allows you to manage components through natural language descriptions.

Features

Create Storyblok components using natural language descriptions
Update existing components with new fields and properties
List all available components
Smart schema generation from descriptions
Support for various field types (text, richtext, asset, multilink, etc.)

Setup

Clone the repository:

git clone [repository-url]
cd storyblok-mcp

Install dependencies:

npm install

Configure environment variables:

cp .env.example .env

Edit .env and add your Storyblok credentials:

STORYBLOK_SPACE_ID: Your Storyblok space ID
STORYBLOK_API_KEY: Your Storyblok API key

Usage

Start the MCP server:

npm start

Creating Components

Create components by providing a description with display name and schema:

display:Component Name

schema:
field1 (text)
field2 (richtext)
field3 (asset)
field4 (multilink)

Updating Components

Update components by specifying their ID and new properties:

display:New Display Name

schema:
newField1 (text)
newField2 (richtext)

Supported Field Types

text: Simple text field
textarea: Multi-line text field
richtext: Rich text editor
markdown: Markdown editor
number: Numeric input
datetime: Date and time picker
boolean: True/false toggle
asset: File/image selector
multilink: Link selector
bloks: Nested components

Development

Run in development mode with auto-reload:

npm run dev

Run tests:

npm test

Cursor MCP Setup

To use this MCP in Cursor, you need to configure it in your Cursor MCP settings:

{
  "mcpServers": {
    "Storyblok MCP": {
      "command": "npx",
      "args": [
        "tsx",
        "/path/to/your/storyblok-mcp/src/main.ts"
      ],
      "env": {
        "STORYBLOK_SPACE_ID": "your_space_id",
        "STORYBLOK_API_KEY": "your_api_key"
      }
    }
  }
}

Replace:

/path/to/your/storyblok-mcp with the actual path where you cloned this repository
your_space_id with your Storyblok space ID
your_api_key with your Storyblok API key

After saving the configuration, restart Cursor for the changes to take effect. You can then use natural language commands to manage your Storyblok components directly from Cursor.

storyblok-mcp FAQ

How do I set up the Storyblok MCP server?

Clone the repository, install dependencies with npm, configure your Storyblok credentials in the .env file, and start the server with npm start.

What field types does Storyblok MCP support for component schemas?

It supports text, richtext, asset, multilink, and other common Storyblok field types.

Can I update existing components using natural language?

Yes, you can update existing components by providing new fields and properties described in natural language.

Does Storyblok MCP generate schemas automatically?

Yes, it features smart schema generation from natural language descriptions to create structured component schemas.

Is authentication required to use Storyblok MCP?

Yes, you need to provide your Storyblok space ID and API key in the environment configuration to authenticate API requests.

Can Storyblok MCP be integrated with other LLM providers?

While primarily designed for Storyblok, it can work with LLMs like OpenAI, Anthropic Claude, and Google Gemini for natural language processing.

How do I list all components using Storyblok MCP?

The server provides functionality to list all available components programmatically via its API.

What is the benefit of using natural language to manage components?

It simplifies content modeling by allowing non-technical users to describe components without manual schema coding.