How to Use the Kontent.ai (Enterprise Headless CMS) MCP in Claude Code

Q: How do I add Kontent.ai (Enterprise Headless CMS) to Claude Code?

Run claude mcp add --transport http -- in your terminal. Make sure to put all transport and header flags before the server name. Claude stores this in /.claude.json.

Q: Does Kontent.ai (Enterprise Headless CMS) allow Claude Code to read taxonomies?

It does. Your CLI agent can pull the full hierarchy via listtaxonomies and inspect specific terms using gettaxonomy. This is perfect for validating tag structures during a CI run.

Bring Kontent.ai into your terminal to automate headless publishing pipelines with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kontent.ai (Enterprise Headless CMS) MCP to Claude Code

Create your Vinkius account to connect Kontent.ai (Enterprise Headless CMS) to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Kontent.ai (Enterprise Headless CMS) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit schemas from the command line

The `list_content_types` tool dumps your entire schema registry straight into your terminal session. Claude Code uses this to verify that your staging environment matches production before running a deployment script. If a build fails due to a missing field, your agent runs `get_content_type` to inspect the exact structural requirements. It identifies the drift, updates your local types, and fixes the build pipeline without you opening a browser.

Run localization syncs via this MCP Server

Managing translations across environments requires heavy automation. Claude Code executes `list_items` to find all entries missing a specific language code. It then loops through the missing entries, calling `upsert_item` if the base container is absent, followed by `upsert_language_variant` to inject the translated text. You can run this entire sequence as a headless cron job.

Trigger deployments and variant publishing

Pushing content live should be part of your deployment script. Claude Code triggers `publish_variant` to release specific language variants to the Delivery APIs right as your frontend builds. It can also audit your media library by running `list_assets` and checking your tag structures with `list_taxonomies`. If everything aligns with your release manifest, it ships the content and logs the output to stdout.

Setup guide

Set up Kontent.ai (Enterprise Headless CMS) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see kontentai-enterprise-headless-cms-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Kontent.ai (Enterprise Headless CMS) transactions." It will automatically discover and invoke the available Kontent.ai (Enterprise Headless CMS) tools.

Terminal

claude mcp add --transport http kontentai-enterprise-headless-cms-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Kontent.ai (Enterprise Headless CMS) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "kontentai-enterprise-headless-cms-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Kontent.ai. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Kontent.ai (Enterprise Headless CMS) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Kontent.ai (Enterprise Headless CMS) MCP in Claude Code

Run `claude mcp add --transport http -- ` in your terminal. Make sure to put all transport and header flags before the server name. Claude stores this in `~/.claude.json`.

Yes. You can write a bash script that pipes translation files into Claude Code. The agent will read the files and execute `upsert_language_variant` to update the draft content in the CMS.

It does. Your CLI agent can pull the full hierarchy via `list_taxonomies` and inspect specific terms using `get_taxonomy`. This is perfect for validating tag structures during a CI run.

Speed and automation. Instead of clicking through a UI, you can trigger `publish_variant` directly from a GitHub Action or a deployment script to keep your content in sync with your code releases.

Your schema definitions and taxonomy trees remain entirely isolated. Claude Code executes the API calls locally on your host machine or runner. The server only transmits the exact JSON payloads required to complete the requested operation, ensuring your structural IP never leaks outside your infrastructure.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript