Kontent.ai MCP for AI. Control your headless CMS with natural language.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
How this MCP server connects to your AI agent
Kontent.ai MCP lets you manage structured content, assets, and taxonomies through natural language prompts. Get immediate access to Kontent's Delivery and Management APIs, letting your AI agent read specific articles, create new content types, or audit entire collections without touching the web console.
What AI agents can do with Kontent.ai Automation
Delivery get item
Fetches the full details for one specific content item using its unique identifier.
Delivery list items
Retrieves a list of multiple content items, supporting filtering by type or collection depth.
Delivery list taxonomies
Lists all taxonomy groups defined in your project's structure.
Fetch individual articles or asset details when you know the exact item code.
List multiple content items, types, or taxonomy groups based on filters like collection or depth.
Build out the CMS by creating new content types, taxonomies, or asset records.
Update existing content items, change language variants, or clean up old assets.
Ask an AI about this
Waiting for input…
What AI agents can do with Kontent.ai MCP with 21 Tools
These tools let your agent interact with every function of Kontent.ai's CMS, from reading specific assets to defining entire content types.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Kontent.ai on VinkiusDelivery Get Item
Fetches the full details for one specific content item using its unique identifier.
Delivery List Items
Retrieves a list of multiple content items, supporting filtering by type or...
Delivery List Taxonomies
Lists all taxonomy groups defined in your project's structure.
Delivery List Types
Gets a list of all available content types (schemas) used across the CMS.
Manage List Assets
Provides an overview and list of all digital assets attached to your project.
Manage Create Asset
Uploads and registers a new asset (like an image or PDF) into the CMS repository.
Manage Create Item
Generates a brand-new content item record, populating it with initial data.
Manage Create Taxonomy
Establishes an entirely new taxonomy group to categorize your content.
Manage Create Type
Defines a completely new content structure or schema for the CMS.
Manage Delete Asset
Removes an asset from your project's repository entirely.
Manage Delete Item
Permanently deletes a content item record from the CMS.
Manage Delete Taxonomy
Removes an entire taxonomy group, which will orphan any associated content.
Manage Delete Type
Deletes a defined content type schema from the CMS structure.
Manage Get Variant
Retrieves a specific language version of an existing content item.
Manage List Items
Lists all content items when you need to see the current state of your records.
Manage List Taxonomies
Provides a list of existing taxonomies, useful for auditing and planning changes.
Manage List Types
Lists all available content types to check the current CMS schema definitions.
Manage Update Asset
Modifies an existing asset, such as changing its metadata or associated file path.
Manage Update Item
Changes the content of an existing item, like editing text or updating a date field.
Manage Update Taxonomy
Modifies the settings or scope of an existing taxonomy group.
Manage Update Type
Changes the fields or structure definition of a content type schema.
Manage Update Variant
Updates specific translated text or data for one language version of an item.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Kontent.ai integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Kontent.ai, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Built on the Model Context Protocol (MCP) for Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 22 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
The Content CMS is a Black Box of Clicks, Solved with Vinkius AI Gateway
Today, updating content requires jumping between dozens of tabs. You click into the 'Assets' library, then you navigate to the correct collection, filter by language, find the article, and then finally open its draft editor just to change a single word or update an image link. It’s tedious copy-pasting across multiple screens.
With this MCP, that entire process vanishes. You simply tell your agent, 'Update the hero banner image on all blog posts.' The system handles locating the right content item, updating the asset reference, and saving it—all in one go.
Kontent.ai: Full Schema Control
The biggest manual headache is defining a new piece of data. If you need to track 'Author Bio' fields or 'Associated Legal Document' links, you used to file a ticket with development and wait days for the schema change. You were stuck waiting on someone else’s schedule.
Now, you use manage_create_type. Your agent executes this tool, defining the new field requirements instantly. That means you get structural changes implemented in minutes, not days.
What your AI can actually do with this
Managing a headless CMS shouldn't feel like navigating a decade-old web application. This MCP connects your AI client directly to Kontent.ai's core structure, giving you full control over both delivery and management functions. You can ask your agent things like, 'List all blog posts from the last quarter that mention sustainability,' or 'Create a new content type for case studies.' Need to fix an asset? Just tell it to update the image linked to a specific page item.
If your existing stack uses multiple tools, Vinkius makes sure this MCP is available right alongside them, giving you one central point of control. It handles everything from fetching data using the Delivery API to building out new content structures via the Management API.
019ea5f5-2693-733c-a7aa-4bc730240881 
Here's how it actually works
The bottom line is you never have to switch from chatting with your AI agent to navigating Kontent's admin panel again.
Subscribe to this MCP on Vinkius and provide your Kontent.ai Project ID along with the necessary Delivery and Management API keys.
Your AI client recognizes the available tools, making it ready to accept structured requests about your content structure.
You ask your agent a plain language question—like 'What are all my product categories?'—and it uses the correct tool to deliver the data.
Who is this actually for?
This MCP is for anyone whose job involves structured content. If you spend time auditing taxonomy tags, checking asset lifecycles, or building out new content models, this tool saves hours of manual clicking and cross-referencing.
Auditing thousands of content items across multiple collections. They use the delivery_list_items to quickly audit content or the manage_update_item tool to fix typos in language variants.
Integrating CMS data into a front-end build. They use delivery_get_item and delivery_list_types to fetch schemas and payloads directly for development testing.
Defining the structure of new content. They use manage_create_type, manage_create_taxonomy, and manage_create_asset to build out a brand-new data model or category system.
What Changes When You Connect
Audit content across languages instantly. You can use manage_get_variant and delivery_list_items to check the translated text for every single item in a collection, avoiding manual checks in multiple UI tabs.
Build complex data structures on demand. Need a new type? Use manage_create_type and define it right from your chat interface, specifying all required fields before any developer writes code.
Maintain content cleanliness automatically. Instead of manually deleting old assets or obsolete taxonomies, tell the agent to run cleanup using manage_delete_asset or manage_delete_taxonomy.
Accelerate development time. Developers can use delivery_list_types and delivery_get_item to pull schemas and payloads directly into their IDE for rapid integration testing, bypassing manual API endpoint calls.
Manage content lifecycle fully. You don't just retrieve data; you control it. Use manage_create_item or manage_update_item to push new drafts or corrections live with simple prompts.
See it in action
Updating a global campaign message
The marketing team needs to change the boilerplate copy on 50 product pages across four different languages. They ask their agent, 'Update all items of type 'product_page' with the new Q3 slogan.' The MCP handles this using manage_update_item and manages multiple language variants, saving them from editing each item individually.
Restructuring product data
The e-commerce team realizes they need to track 'Sustainability Score' on every product. They ask the agent to define a new field. The MCP responds by executing manage_create_type, defining the necessary schema and making the change available across all future content.
Analyzing old content for cleanup
A junior developer needs to find every item that hasn't been updated in three years. They prompt the agent, 'List items older than 1095 days.' The MCP uses delivery_list_items with advanced filtering, providing a clean list of stale records they can then triage.
Preparing for new content lines
The content team needs to start writing guides on 'AI Ethics' but has no category for them. They ask the agent to help organize it. The MCP executes manage_create_taxonomy, setting up a dedicated taxonomy group that keeps the new content separated and structured.
The honest tradeoffs
Treating it like a simple database lookup
The user asks: 'Give me all articles about climate change.' This assumes the AI knows how to query across collections, types, and taxonomies simultaneously.
Instead of asking for everything at once, ask the agent to list content items using delivery_list_items. Then, if needed, use manage_list_taxonomies first to narrow down the search scope.
Attempting complex data migration in a single prompt
The user asks: 'Move all old articles into a new category and update their metadata.' This requires multiple, sequential steps (read, create, write, delete), which is too much for one command.
Break the task down. First, use manage_create_taxonomy to build the target group. Then, use delivery_list_items to identify the content IDs, and finally, instruct the agent to run manages_update_item on those IDs.
Forgetting structural dependencies
The user tries to delete a taxonomy without checking if any content still references it. This fails because the CMS prevents orphaned data deletion.
Always check first by running delivery_list_items and then, if necessary, use manage_update_taxonomy or manage_list_taxonomies to verify that all required dependencies are handled before attempting a delete.
When It Fits, When It Doesn't
Use this MCP if your primary workflow revolves around structured content: managing article bodies, tracking assets, defining content schemas, or auditing taxonomy tags. If you need to perform any action where data exists in distinct types (e.g., 'product' vs. 'blog post') and needs controlled structure, this is what you use. Don't use it if your goal is merely sending an email or pulling real-time stock market quotes; for those, look for messaging or finance MCPs. If you only need to read public data but never want to write back (e.g., just reading product lists), the Delivery API tools are sufficient and safer than using the full Management suite.
Questions you might have
How do I update an item using the Kontent.ai MCP? +
You use manage_update_item to modify content. You just need to give the agent the unique ID of the item and tell it exactly which fields to change, like updating text or changing a date.
Can I list all available content types with the Kontent.ai MCP? +
Yes, you use delivery_list_types. This tool shows you every schema currently defined in your project, so you know what kind of content exists to work with.
What's the difference between listing items and managing them via Kontent.ai MCP? +
delivery_list_items reads data (viewing). manage_list_items is used when you want to list records that might be candidates for modification or cleanup.
How do I add a new category in Kontent.ai using this MCP? +
To create a new category, use manage_create_taxonomy. You specify the name and scope of the taxonomy group, and the tool handles its creation.
Do I need to know specific IDs when I use delivery_get_item? +
Yes, deliver_get_item requires a unique identifier for the content item. If you don't have the ID, start by using delivery_list_items to find it first.
We've already built the connector for Kontent.ai. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 22 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.