How to Use the Amplience MCP in OpenAI Agents SDK

Q: Can I run safe content deletions using Amplience and OpenAI Agents SDK?

Yes. The deletecontentitem tool requires explicit version validation before it removes anything. Your agent must fetch the current schema lock first to prevent accidental database wipes.

Q: Do I need to manually map the content schemas?

No. The getcontentitem tool fetches the exact schema revision lock alongside the content configuration. Your agent reads this structure dynamically to build valid update payloads.

Manage Amplience CMS content directly within your OpenAI Agents SDK workflows using verified, secure schema validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amplience MCP to OpenAI Agents SDK

Create your Vinkius account to connect Amplience to OpenAI Agents SDK 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 Amplience with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Amplience CMS updates safely via OpenAI Agents SDK

The `create_content_item` tool lets your agent construct structured content inside specific folder paths. Your agent reads the required schema first, drafts the payload, and writes it directly to the CMS. This MCP Server works within the SDK's native guardrails to protect your live environment. Before execution, your system validates the proposed JSON payload against your content repository rules.

Fast content discovery and workspace traversal

Finding assets starts with `list_hubs`, which fetches all active environments your agent has permission to access. From there, the agent runs `list_repositories` and `list_folders` to map out the entire content tree. Instead of manual lookups, the agent runs `list_content_items` to pull paginated lists of assets over the MCP connection. It locates the exact files needing updates in seconds.

Direct publishing to the live delivery CDN

The `publish_content_item` tool pushes approved content versions directly to production distribution channels. Your agent verifies the structural layout first by calling `get_delivery_content` to check the live CDN blocks. If a drafted item needs modifications before release, `update_content_item` modifies the structure to match the current schema. You get full execution tracing on your OpenAI dashboard for every single publish event.

Setup guide

Set up Amplience MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Amplience tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Amplience tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Amplience tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Amplience Agent",
            instructions="You have access to Amplience tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 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.

Why Choose Vinkius

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

Connect Amplience 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 Amplience MCP in OpenAI Agents SDK

You register the MCP Server URL using the HTTP streamable transport class in Python. The SDK automatically discovers the ten available tools.

Yes. The `delete_content_item` tool requires explicit version validation before it removes anything. Your agent must fetch the current schema lock first to prevent accidental database wipes.

Set the cache tools flag to true when initializing your agent. This prevents constant network round-trips for MCP tool definitions and keeps execution fast.

No. The `get_content_item` tool fetches the exact schema revision lock alongside the content configuration. Your agent reads this structure dynamically to build valid update payloads.

All API requests run in sandboxed V8 isolates, meaning your raw CMS content and credentials never persist on external servers. This MCP setup uses ephemeral tokens to modify your hubs.

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