Kontent.ai MCP Server

Transform your content operations with AI-powered tools for Kontent.ai. Create, manage, and explore your structured content through natural language conversations in your favorite AI-enabled editor.

Kontent.ai MCP Server implements the Model Context Protocol to connect your Kontent.ai projects with AI tools like Claude, Cursor, and VS Code. It enables AI models to understand your content structure and perform operations through natural language instructions.

✨ Key Features

🚀 Rapid prototyping: Transform your diagrams into live content models in seconds
📈 Data Visualisation: Visualise your content model in any format you want

✨ Key Features
🔌 Quickstart
🛠️ Available Tools
⚙️ Configuration
🚀 Transport Options
💻 Development
License

🔌 Quickstart

🔑 Prerequisites

Before you can use the MCP server, you need:

A Kontent.ai account - Sign up if you don't have an account.
A project - Create a project to work with.
Management API key - Create a Management API key with appropriate permissions.
Environment ID - Get your environment ID.

🛠 Setup Options

You can run the Kontent.ai MCP Server with npx:

STDIO Transport

npx @kontent-ai/mcp-server@latest stdio

Streamable HTTP Transport

npx @kontent-ai/mcp-server@latest shttp

🛠️ Available Tools

Patch Operations Guide

get-patch-guide – 🚨 REQUIRED before any patch operation. Get patch operations guide for Kontent.ai Management API by entity type

Content Type Management

get-type-mapi – Get Kontent.ai content type by internal ID from Management API
list-content-types-mapi – Get all Kontent.ai content types from Management API
add-content-type-mapi – Add new Kontent.ai content type via Management API
patch-content-type-mapi – Update an existing Kontent.ai content type by codename using patch operations (move, addInto, remove, replace)
delete-content-type-mapi – Delete a Kontent.ai content type by codename

Content Type Snippet Management

get-type-snippet-mapi – Get Kontent.ai content type snippet by internal ID from Management API
list-content-type-snippets-mapi – Get all Kontent.ai content type snippets from Management API
add-content-type-snippet-mapi – Add new Kontent.ai content type snippet via Management API
patch-type-snippet-mapi – Update an existing Kontent.ai content type snippet by internal ID using patch operations (move, addInto, remove, replace)
delete-type-snippet-mapi – Delete a Kontent.ai content type snippet by codename

Taxonomy Management

get-taxonomy-group-mapi – Get Kontent.ai taxonomy group by internal ID from Management API
list-taxonomy-groups-mapi – Get all Kontent.ai taxonomy groups from Management API
add-taxonomy-group-mapi – Add new Kontent.ai taxonomy group via Management API
patch-taxonomy-group-mapi – Update Kontent.ai taxonomy group using patch operations (addInto, move, remove, replace) via Management API
delete-taxonomy-group-mapi – Delete Kontent.ai taxonomy group by internal ID

Content Item Management

get-item-mapi – Get Kontent.ai item by internal ID from Management API
get-latest-variant-mapi – Get latest version of Kontent.ai language variant from Management API
get-published-variant-mapi – Get published version of Kontent.ai language variant from Management API
list-variants-item-mapi – List all Kontent.ai language variants of a content item from Management API
list-variants-collection-mapi – List Kontent.ai language variants by collection from Management API (paginated)
list-variants-type-mapi – List Kontent.ai language variants by content type from Management API (paginated)
list-variants-components-type-mapi – List Kontent.ai language variants containing components of a specific content type from Management API (paginated)
list-variants-space-mapi – List Kontent.ai language variants by space from Management API (paginated)
add-content-item-mapi – Add new Kontent.ai content item via Management API. This creates the content item structure but does not add content to language variants. Use create-language-variant-mapi to add content to the item
update-content-item-mapi – Update existing Kontent.ai content item by internal ID via Management API. The content item must already exist - this tool will not create new items
delete-content-item-mapi – Delete Kontent.ai content item by internal ID from Management API
create-language-variant-mapi – Create Kontent.ai variant assigning current user as contributor. Element values must fulfill limitations and guidelines defined in content type
update-language-variant-mapi – Update Kontent.ai language variant of a content item via Management API. Element values must fulfill limitations and guidelines defined in content type. Only provided elements will be modified
create-variant-version-mapi – Create new version of Kontent.ai language variant via Management API. This operation creates a new version of an existing language variant, useful for content versioning and creating new drafts from published content
delete-language-variant-mapi – Delete Kontent.ai language variant from Management API
filter-variants-mapi – Filter Kontent.ai items with variants returning references (item ID + language ID). Use for exact keyword matching and finding specific terms in content. Supports full filtering capabilities (content types, workflow steps, taxonomies, spaces, collections, publishing states, etc.). Returns paginated results with continuation token for fetching subsequent pages. Use bulk-get-items-variants-mapi to retrieve full content for matched items
bulk-get-items-variants-mapi – Bulk get Kontent.ai content items with their language variants by item and language reference pairs. Use after filter-variants-mapi to retrieve full content data for specific item+language pairs. Items without a variant in the requested language return the item without the variant property. Returns paginated results with continuation token
search-variants-mapi – AI-powered semantic search for finding content by meaning and concepts in a specific language variant. Use for: conceptual searches when you don't know exact keywords. Limited filtering options (variant ID only)

Asset Management

get-asset-mapi – Get a specific Kontent.ai asset by internal ID from Management API
list-assets-mapi – Get all Kontent.ai assets from Management API
update-asset-mapi – Update Kontent.ai asset by internal ID

Asset Folder Management

list-asset-folders-mapi – List all Kontent.ai asset folders
patch-asset-folders-mapi – Modify Kontent.ai asset folders using patch operations (addInto to add new folders, rename to change names, remove to delete folders)

Language Management

list-languages-mapi – Get all Kontent.ai languages from Management API (includes both active and inactive - check is_active property)
add-language-mapi – Add new Kontent.ai language via Management API (languages are always created as active)
patch-language-mapi – Update Kontent.ai language using replace operations via Management API (only active languages can be modified - to activate/deactivate, use the Kontent.ai web UI)

Collection Management

list-collections-mapi – Get all Kontent.ai collections from Management API. Collections set boundaries for content items in your environment and help organize content by team, brand, or project
patch-collections-mapi – Update Kontent.ai collections using patch operations (addInto to add new collections, move to reorder, remove to delete empty collections, replace to rename)

Space Management

list-spaces-mapi – Get all Kontent.ai spaces from Management API
add-space-mapi – Add Kontent.ai space to environment
patch-space-mapi – Patch Kontent.ai space using replace operations
delete-space-mapi – Delete Kontent.ai space

Role Management

list-roles-mapi – Get all Kontent.ai roles from Management API. Requires Enterprise or Flex plan with "Manage custom roles" permission

Workflow Management

list-workflows-mapi – Get all Kontent.ai workflows from Management API. Workflows define the content lifecycle stages and transitions between them
add-workflow-mapi – Create a new Kontent.ai workflow via Management API. Define custom workflow steps, transitions, scopes (content types and collections), and role permissions
update-workflow-mapi – Update an existing Kontent.ai workflow by ID via Management API. Modify steps, transitions, scopes, and role permissions. Cannot remove steps that are in use
delete-workflow-mapi – Delete a Kontent.ai workflow by ID via Management API. The workflow must not be in use by any content items
change-variant-workflow-step-mapi – Change the workflow step of a language variant in Kontent.ai. This operation moves a language variant to a different step in the workflow, enabling content lifecycle management such as moving content from draft to review, review to published, etc.
publish-variant-mapi – Publish or schedule a language variant of a content item in Kontent.ai. This operation can either immediately publish the variant or schedule it for publication at a specific future date and time with optional timezone specification
unpublish-variant-mapi – Unpublish or schedule unpublishing of a language variant of a content item in Kontent.ai. This operation can either immediately unpublish the variant (making it unavailable through the Delivery API) or schedule it for unpublishing at a specific future date and time with optional timezone specification

⚙️ Configuration

The server supports two modes, each tied to its transport:

Transport	Mode	Authentication	Use Case
STDIO	Single-tenant	Environment variables	Local communication with a single Kontent.ai environment
Streamable HTTP	Multi-tenant	Bearer token per request	Remote/shared server handling multiple environments

Single-Tenant Mode (STDIO)

Configure credentials via environment variables:

Variable	Description	Required
KONTENT_API_KEY	Your Kontent.ai Management API key	✅
KONTENT_ENVIRONMENT_ID	Your environment ID	✅
appInsightsConnectionString	Application Insights connection string for telemetry	❌
projectLocation	Project location identifier for telemetry tracking	❌
manageApiUrl	Custom Management API base URL (for preview environments)	❌

Multi-Tenant Mode (Streamable HTTP)

For the Streamable HTTP transport, credentials are provided per request:

Environment ID as a URL path parameter: /{environmentId}/mcp
API Key via Bearer token in the Authorization header: Authorization: Bearer <api-key>

This allows a single server instance to handle requests for multiple Kontent.ai environments without requiring credential environment variables.

Variable	Description	Required
PORT	Port for HTTP transport (defaults to 3001)	❌
appInsightsConnectionString	Application Insights connection string for telemetry	❌
projectLocation	Project location identifier for telemetry tracking	❌
manageApiUrl	Custom Management API base URL (for preview environments)	❌

🚀 Transport Options

📟 STDIO Transport

To run the server with STDIO transport, configure your MCP client with:

{
  "kontent-ai-stdio": {
      "command": "npx",
      "args": ["@kontent-ai/mcp-server@latest", "stdio"],
      "env": {
        "KONTENT_API_KEY": "<management-api-key>",
        "KONTENT_ENVIRONMENT_ID": "<environment-id>"
      }
    }
}

🌊 Streamable HTTP Transport (Multi-Tenant)

Streamable HTTP transport serves multiple Kontent.ai environments from a single server instance. Each request provides credentials via URL path parameters and Bearer authentication.

First start the server:

npx @kontent-ai/mcp-server@latest shttp

Create a .vscode/mcp.json file in your workspace:

{
  "servers": {
    "kontent-ai-multi": {
      "uri": "http://localhost:3001/<environment-id>/mcp",
      "headers": {
        "Authorization": "Bearer <management-api-key>"
      }
    }
  }
}

For secure configuration with input prompts:

{
  "inputs": [
    {
      "id": "apiKey",
      "type": "password",
      "description": "Kontent.ai API Key"
    },
    {
      "id": "environmentId",
      "type": "text",
      "description": "Environment ID"
    }
  ],
  "servers": {
    "kontent-ai-multi": {
      "uri": "http://localhost:3001/${inputs.environmentId}/mcp",
      "headers": {
        "Authorization": "Bearer ${inputs.apiKey}"
      }
    }
  }
}

Update your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

Use mcp-remote as a proxy to add authentication headers:

{
  "mcpServers": {
    "kontent-ai-multi": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://localhost:3001/<environment-id>/mcp",
        "--header",
        "Authorization: Bearer <management-api-key>"
      ]
    }
  }
}

Add the server using the CLI:

claude mcp add --transport http kontent-ai-multi \
  "http://localhost:3001/<environment-id>/mcp" \
  --header "Authorization: Bearer <management-api-key>"

Note: You can also configure this in your Claude Code settings JSON with the url and headers properties.

[!IMPORTANT] Replace <environment-id> with your Kontent.ai environment ID (GUID) and <management-api-key> with your Management API key.

💻 Development

🛠 Local Installation

# Clone the repository
git clone https://github.com/kontent-ai/mcp-server.git
cd mcp-server

# Install dependencies
npm ci

# Build the project
npm run build

# Start the server
npm run start:stdio  # For STDIO transport
npm run start:shttp  # For Streamable HTTP transport

# Start the server with automatic reloading (no need to build first)
npm run dev:stdio  # For STDIO transport
npm run dev:shttp  # For Streamable HTTP transport

📂 Project Structure

src/ - Source code
- tools/ - MCP tool implementations
- clients/ - Kontent.ai API client setup
- schemas/ - Data validation schemas
- utils/ - Utility functions
  - errorHandler.ts - Standardized error handling for MCP tools
  - throwError.ts - Generic error throwing utility
- server.ts - Main server setup and tool registration
- bin.ts - Single entry point that handles both transport types

🔍 Debugging

For debugging, you can use the MCP inspector:

npx @modelcontextprotocol/inspector -e KONTENT_API_KEY=<key> -e KONTENT_ENVIRONMENT_ID=<env-id> node path/to/build/bin.js

Or use the MCP inspector on a running streamable HTTP server:

npx @modelcontextprotocol/inspector

This provides a web interface for inspecting and testing the available tools.

📦 Release Process

To release a new version:

Bump the version using npm version [patch|minor|major] - this updates package.json, package-lock.json, and syncs to server.json
Push the commit to your branch and create a pull request
Merge the pull request
Create a new GitHub release with the version number as both name and tag, using auto-generated release notes
Publishing the release triggers an automated workflow that publishes to npm and GitHub MCP registry

License

MIT

Kontent.ai