How to Use the Builder MCP in OpenAI Agents SDK

Q: How does OpenAI Agents SDK handle schema mismatches in Builder?

The agent uses getmodelschema to inspect the structure before writing. If the schema changes on your CMS, the agent detects the difference and adjusts its payload, or halts execution if a strict guardrail fails.

Q: Is there a way to track Builder media assets with this setup?

Use getmediafile to inspect assets. Your OpenAI agent retrieves the media metadata to verify image dimensions or file sizes before inserting them into a visual block.

Drive Builder.io headless CMS workflows directly from your OpenAI Agents SDK production pipelines with strict guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Builder MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Builder schemas in OpenAI Agents SDK

`get_model_schema` fetches the exact field definitions of your Builder space so your OpenAI Agents SDK runner never pushes broken JSON payloads. The agent reads the structure first, ensuring any subsequent content creation matches your exact types. Running this inside an OpenAI agent with guardrails prevents bad writes. If the agent tries to send an invalid field, the validation layer catches it before it hits your production site.

Safe visual block edits via MCP Server

`create_visual_block` and `update_visual_block` let your OpenAI Agents SDK pipeline write directly to your visual canvas. The agent drafts, modifies, or replaces layout blocks based on real-time user prompts or scheduled updates. Tracing on the OpenAI dashboard lets you audit every single layout change. You see exactly which agent initiated the edit and what the visual payload looked like before it went live.

Pruning stale content safely

`wipe_visual_block` removes outdated blocks from your models, keeping your production headless CMS clean. Your OpenAI Agents SDK setup uses this MCP tool to clean up expired promotional banners or temporary event pages. Safe handoffs between your discovery agent and your cleanup agent ensure no active pages get deleted. The discovery agent runs `list_model_content` to find expired items, then passes the ID to the cleanup agent for deletion.

Setup guide

Set up Builder 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 Builder tools at runtime.
3

Create your Agent

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

Run the agent

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

Install openai-agents first, then instantiate MCPServerStreamableHttp with your Vinkius endpoint URL. Pass this server instance in the mcp_servers list when initializing your Agent. Set cacheToolsList=True so your OpenAI agent does not waste time fetching the tool definitions on every turn.

Yes, you can control tool access directly in your Python code by defining specialized agents. For example, your editorial agent only gets access to list_model_content and get_single_content, while your admin agent gets access to wipe_visual_block.

The agent uses get_model_schema to inspect the structure before writing. If the schema changes on your CMS, the agent detects the difference and adjusts its payload, or halts execution if a strict guardrail fails.

Use get_media_file to inspect assets. Your OpenAI agent retrieves the media metadata to verify image dimensions or file sizes before inserting them into a visual block.

Vinkius runs the server in an isolated V8 sandbox, meaning your API tokens never leak to the LLM or other tenants. Your OpenAI Agents SDK calls pass through a single secure endpoint token, keeping your CMS schemas and visual blocks safe.

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