Amplience MCP. Manage your entire CMS workflow via chat commands.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Amplience lets your AI agent talk directly to its headless CMS. You can query asset structures, pull product metadata, create new blog drafts, and publish content updates live—all through a chat interface.
What your AI agents can do
Create content item
Writes and adds a completely new structured content item into a specified folder.
Delete content item
Removes an existing content item from the repository after confirming version details.
Get content item
Pulls the full configuration and revision lock of a specific piece of content data.
The agent maps out the entire content structure by listing accessible Hubs, Repositories, and internal folders.
You pull complete metadata for existing items, including their current schema rules and validation requirements.
The agent writes brand new content pieces or product entries by pushing correctly formatted JSON payloads into the system.
You modify specific fields or data structures within an existing item without recreating it.
The agent executes the final step, pushing a content version directly out to the live delivery CDN.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Amplience: 10 Tools for Content Architecture
These tools give you full control over the content lifecycle in Amplience. You can read data structures, write new items, modify existing drafts, and push everything live.
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 Amplience on Vinkius019d754dcreate content item
Writes and adds a completely new structured content item into a specified folder.
019d754ddelete content item
Removes an existing content item from the repository after confirming version details.
019d754dget content item
Pulls the full configuration and revision lock of a specific piece of content data.
019d754dget delivery content
Retrieves the exact structural details needed for verifying CDN delivery blocks on the live site.
019d754dlist content items
Gets a paginated list of all content items available within a specific repository.
019d754dlist folders
Shows a list of folders that organize content inside a given repository.
019d754dlist hubs
Lists all major accessible Amplience environments or workspaces.
019d754dlist repositories
Shows all specific content storage areas within a defined Hub.
019d754dpublish content item
Pushes an edited content item version out to the live delivery CDN for immediate viewing.
019d754dupdate content item
Modifies and saves changes to all data fields of an existing content piece matching its current schema.
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 Amplience, then connect any of our 4,800+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,800+ 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 Amplience. 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
Works with 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 server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
It's annoying having to click through five different tabs just to check one asset's status.
Today, updating even a small component is a manual nightmare. You have to log into the CMS, find the specific content type (e.g., 'Hero Banner'), navigate to the correct repository, click on the item ID, check the metadata fields for typos, make your change, and then manually hit the 'Publish' button—all while hoping you didn't miss a required field.
With this MCP, you just talk to your agent. You tell it what needs changing. The agent pulls the content details for you, validates that the schema is ready, performs the update via `update_content_item`, and then hits the live CDN with one command. It's pure conversation.
The Content Item Schema Lock: Get Data Integrity with get_content_item
Before making a single change, you have to worry about whether the underlying data structure—the schema lock—has changed since last week. You'd usually have to export and compare massive JSON payloads just to verify if your script is still pointing at valid fields.
Now, simply ask the agent to run `get_content_item`. It returns the full schema details right alongside the payload. This guarantees that whatever you are modifying matches the current ruleset—no guesswork needed.
What you can do with this MCP connector
Need to manage enterprise content without logging into the CMS dashboard? This MCP links Amplience to any intelligent AI client so you can handle your entire content life cycle natively. Your agent discovers asset hierarchies by listing available Hubs and Repositories, making sure it knows exactly where every piece of data lives.
You can pull complex structured metadata—like checking a specific item's schema lock—and then tell the system to update or create new drafts based on that structure. When your content needs to hit the live site, you just instruct the agent to publish it. This capability is powerful because you don't have to jump through multiple systems; if you're building an automation that pulls data from Amplience and sends it out via another platform, Vinkius handles all the secure connections in transit, letting your agent focus on what matters: writing code or drafting copy.
019d754d-eb67-7197-8165-6632cbc1033f 
How Amplience MCP Works
- 1 First, enable the connector inside your environment and submit your specific Amplience Hub Name along with a Personal Access Token.
- 2 Next, use any MCP-compatible client to prompt the agent. For example, asking it to list all available repositories or pull the schema details for an item ID.
- 3 The agent executes the command, pulls the structured data back, and you can then direct it to create, update, or publish the content.
The bottom line is: your AI client treats your CMS like just another API endpoint; it's conversational.
Who Is Amplience MCP For?
Anyone who spends time updating e-commerce banners, managing product descriptions, or drafting content across multiple platforms. It’s for the person tired of clicking through dozens of tabs and copy-pasting data from one tool into another.
Needs to rapidly find a specific banner configuration block, update its URL path, and ensure that change goes live immediately for Black Friday.
Needs the agent to read the precise output validation structure of an Amplience schema so they can automatically scaffold a corresponding type-safe interface in their code editor.
Wants to command the agent to create a brand new promotional blog post draft, pre-populating all fields using specific SEO guidelines without touching the CMS UI.
What Changes When You Connect
- Need to update a product banner? Instead of navigating through multiple menus, you can ask the agent to run
get_content_itemand then useupdate_content_itemto change the text or image path directly. - Don't know where your content lives? Run
list_hubsfirst. This maps out all available environments so you know which workspace to target before running any other commands. - Saving time on publishing is huge. After drafting a blog post using
create_content_item, you can then usepublish_content_itemto push it live instantly, bypassing manual review queues. - Developers can trust the data by first calling
get_content_itemto check its schema revision lock before writing any code against it. This keeps your application type-safe and stable. - If you're unsure if content has made it to the public site, run
get_delivery_content. It verifies that the structural data is correctly mapped for the edge delivery API.
Real-World Use Cases
The E-commerce Manager needs an urgent banner change.
A manager spots a typo on the Black Friday hero banner. Instead of logging into the CMS, they tell their agent to run get_content_item for that specific ID. They review the metadata and then use update_content_item, followed by publish_content_item. The change is live in minutes.
The Developer needs schema validation.
A frontend developer can't figure out the required input type for a new component. They ask the agent to run get_content_item on a similar piece of content, pulling back the full schema lock and payload structure immediately.
The Content Team needs to audit assets.
Before starting a campaign, the team wants to know which types of content exist. They ask the agent to list_hubs first, then use that information with list_repositories to get a full map of all available data sources.
The Agent needs to clean up old drafts.
A user has finished a campaign and wants to remove all draft assets from the system. They ask the agent to list_content_items in that repository, identify the IDs of the old content, and then run delete_content_item on each one.
The Tradeoffs
Assuming structure is stable.
A developer tries to write a script that assumes every product page will have a 'Title' field, but the schema changes next month and the script breaks.
→
Always run get_content_item first. This validates the current schema lock against your expected payload structure before you attempt any writing or reading operations.
Forgetting to publish after an update.
The marketer updates a critical landing page's copy using update_content_item, but forgets the final step, leaving the old content visible on the live site.
→
After any successful modification, you must run publish_content_item. This is what physically pushes the new data out to the edge delivery API.
Trying to find a resource without knowing where it lives.
The user knows they need 'Q3 assets' but doesn't know if those are in the 'Main Hub' or the 'Marketing Hub'.
→
Start by asking the agent to run list_hubs. This gives you all accessible environments, letting you narrow down your search to the right workspace.
When It Fits, When It Doesn't
Use this MCP if your workflow requires deep interaction with structured content—creating, modifying, and deploying assets programmatically. If your goal is simply to read a single piece of public data (like viewing an article draft), you might just use the CMS's built-in UI. But if that content needs to feed into another system, or if you need to verify its technical schema lock first, this MCP is required. Don't use it if you only want to read basic site copy; use get_content_item. Only use it for complex deployments when you have the necessary credentials and a clear idea of which content repository needs action.
Common Questions About Amplience MCP
How do I find out what content repositories I can access using list_repositories? +
You first need to run list_hubs to select your environment. Once you have the Hub name, then use list_repositories to get a full directory of all available storage areas within that specific workspace.
What is the difference between create_content_item and update_content_item? +
Use create_content_item when you are building something brand new, like a first draft for an article. Use update_content_item when the asset already exists and you just need to change some fields or text within it.
Can I publish content without manually running the publication step? +
No, you must explicitly run publish_content_item. This action tells the system to take the version you've edited and push it out to the live CDN. Otherwise, changes stay trapped in draft status.
How do I check if my content is actually showing on the front end? +
You run get_delivery_content. This checks the structural matching for the Delivery CDN blocks and confirms that the data is correctly formatted for the live website.
How do I check which Amplience environments are available using list_hubs? +
The list_hubs tool retrieves every accessible environment name. This is crucial for knowing exactly where your content lives before running any other commands. You must specify the correct Hub Name to ensure your agent reads from development, staging, or production data.
If my schema structure changes, how does get_content_item help me validate it? +
It fetches both the content payload and its current schema revision lock. By reading this locked metadata first, your agent knows precisely what fields are expected. You can use this read-only data to verify that any subsequent update_content_item attempt will pass validation.
How do I pull a large amount of content data using list_content_items? +
The tool handles pagination, allowing you to retrieve massive amounts of structured content in manageable chunks. Instead of hitting rate limits, the agent iterates through pages until all items are accounted for. This makes bulk reporting efficient.
What precautions does delete_content_item take to prevent accidental data loss? +
The tool requires explicit version validation before executing a permanent deletion. You cannot simply target an ID; the agent must confirm the content item's current revision lock status first. This mandatory check prevents you from deleting live, un-saved versions.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.