- LIVE
- DRAFT
- REVIEW
- ERROR
Short answer
How can I use my AI to publish content to Amplience?
Your agent uses the Amplience API to modify content items and then triggers a publish command to push those changes to the edge. You'll see how the agent handles the update and deployment cycle below.
The outcomes.
Where your changes land.
Depending on your prompt, the agent moves content into one of these states.
LIVE
Content is live
The agent successfully updates the item and pushes it to the CDN. Your changes are now visible to your end users.
DRAFT
Item is updated
The agent modifies the content item in the repository. The changes are saved but haven't been pushed to the edge yet.
REVIEW
Human needed
The agent has prepared the changes but waits for you to confirm the final publish command. You maintain control over the deployment.
ERROR
Update failed
The agent hits a snag with the API or the content structure. You'll get a specific error message to fix the data.
The workflow
What your AI does when the request arrives.
The agent follows a logical path from data modification to edge delivery.
Modify the item
The agent identifies the specific content item you want to change and applies your requested edits to the data fields.
update_content_itemPush to CDN
Once the data is correct, the agent sends the command to make the content live on the delivery network.
publish_content_itemVerify status
The agent checks the response from the Amplience API to ensure the item was saved and the publish was successful.
update_content_itempublish_content_itemConfirm deployment
The agent reports back to you that the content is now at the edge and ready for traffic.
publish_content_item
Try it
Copy these to start.
Use these prompts to trigger the Amplience workflow.
Starting points
Replace the bracketed text with your actual Amplience content IDs or field names.
Amplience Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_JeoiOM8ki8jslAZQLhECHOmHPjVyKZPKjRrtAdGX/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Amplience capabilities are ready to use.
{
"mcpServers": {
"amplience-mcp": {
"url": "https://edge.vinkius.com/vk_preview_JeoiOM8ki8jslAZQLhECHOmHPjVyKZPKjRrtAdGX/mcp"
}
}
}Update the hero banner content item [ID] with the new headline 'Summer Sale'.
Change the price field in the product item [ID] to 49.99 and publish it.
Modify the description for the [ID] content item and push it live to the CDN.
Update the image URL for the [ID] item and then publish the change.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Amplience once, then ask.
You only need to link your Amplience credentials once. After that, your agent handles all the API calls through the Vinkius host.
Connect Amplience to your AIFAQ
How this task behaves
- 01
Can the AI create brand new content items?
No. The agent can only modify existing items or publish items that already exist in your repository.
- 02
Will the AI publish changes without my permission?
The AI only publishes when you explicitly tell it to publish. If you only ask to 'update' an item, it will stay in a draft state.
- 03
Can the AI delete content items?
No. There is no tool available to delete content items, so the agent cannot remove data from Amplience.
- 04
Does the AI handle image uploads?
No. The agent can update a field with a new image URL, but it cannot upload raw binary files to your media library.
- 05
How do I know if the publish worked?
The agent will confirm the success of the publish command based on the API response from Amplience.
More questions about Amplience? See everything the Amplience Connector can do
Connect Amplience to Claude, Cursor, ChatGPT & more
