How to Use the Contentful MCP in OpenAI Agents SDK

Q: How do I manage draft states before publishing?

Your agent uses createentry to generate a draft first. When ready, the agent calls publishentry to make it public, or unpublishentry to revert it back to a draft state.

Build production-ready OpenAI Agents SDK systems that safely read, write, and publish Contentful entries with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Contentful MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarded Contentful space changes with OpenAI Agents SDK

OpenAI Agents SDK intercepts tool calls before execution, letting your agent run `create_entry` or `update_entry` only when safety policies pass. You define the exact validation rules in Python, preventing autonomous agents from messing up your production Contentful spaces. If the agent tries to push an unapproved edit, the SDK catches it. The agent can safely draft content via `create_entry` and queue it for human review before calling `publish_entry` to go live.

Fast schema discovery via OpenAI MCP Server stream

Your OpenAI Agents SDK setup auto-discovers your content structure instantly. By pointing the SDK to this MCP Server, the agent inspects your models with `list_content_types` and `get_content_type` without manual schema mapping. This eliminates the need to hardcode Python classes for every single Contentful model. The agent queries `list_entries` to understand how your fields are structured and starts generating matching payloads on the fly.

Traceable multi-agent handoffs for editorial workflows

Build a multi-agent system where one OpenAI agent searches assets via `list_assets` and another drafts the copy. The SDK manages handoffs between these specialized agents while tracking every single `get_entry` request through the MCP Server interface in your OpenAI dashboard. When a draft is ready, a senior editor agent calls `publish_entry`. If a rollback is needed, another agent executes `unpublish_entry` to revert changes immediately.

Setup guide

Set up Contentful 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 Contentful tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Contentful 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="Contentful Agent",
            instructions="You have access to Contentful 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 Contentful. 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 Contentful 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 Contentful MCP in OpenAI Agents SDK

You should configure backoff handlers directly in your Python code where you initialize the SDK. Since this MCP Server translates agent requests to Contentful's REST API, the SDK will catch rate-limit exceptions and retry the calls automatically.

Yes, you control this by limiting the API token scoped to the connection. The SDK will only discover spaces returned by `list_spaces` that the underlying token has permissions to read or modify.

No, you don't. The SDK dynamically discovers the schema of your content models by executing `get_content_type` through the MCP Server interface at runtime.

Your agent uses `create_entry` to generate a draft first. When ready, the agent calls `publish_entry` to make it public, or `unpublish_entry` to revert it back to a draft state.

Your Contentful API tokens are encrypted at rest and only injected into the ephemeral V8 sandbox during active tool executions. No raw entry payloads or space configurations are stored permanently on Vinkius servers; they stream directly between your OpenAI Agents SDK runtime and the Contentful API.

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