How to Use the Plasmic (Visual Headless Page Builder) MCP in OpenAI Agents SDK

Q: Can the agent publish pages automatically?

Yes. The agent can call publishcmsitem to push draft content live. You can enforce a human-in-the-loop step using OpenAI guardrails before this tool executes.

Q: How is my data handled when querying the database?

The querycmsitems tool accesses your CMS records, which may contain proprietary marketing copy or user data. The Vinkius V8 Isolate Sandbox processes these requests ephemerally, ensuring no persistent local storage of your database contents occurs outside the immediate transaction.

Connect Plasmic (Visual Headless Page Builder) to your OpenAI Agents SDK workflow for safe, traceable CMS operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Plasmic (Visual Headless Page Builder) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Plasmic (Visual Headless Page Builder) to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Plasmic (Visual Headless Page Builder) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Safe CMS Operations via MCP Server

Tools like `create_cms_item` and `update_cms_item` let your OpenAI agents modify Plasmic content directly. You define the guardrails in the agent configuration, ensuring marketing copy updates pass validation before they hit the database. When a specialized copywriter agent finishes a draft, it can hand off to a publisher agent that runs `publish_cms_item`. Every action gets logged in the OpenAI dashboard, giving you full tracing for who changed what layout.

Fetch and Render Project Trees

The `get_model` tool pulls the complete JSON representation of your project element tree right into the agent's context window. Your agent reads the exact SDUI structure, allowing it to understand the current page hierarchy before proposing changes. If you need the final output, the agent calls `render_html` to grab the generated markup for a specific component. This works perfectly with OpenAI's strict tool-calling constraints, ensuring predictable data retrieval.

Programmatic Layout Updates

Use `update_project` to let your agent push structural changes to Plasmic programmatically. Instead of clicking through a visual interface, your Python code dictates how components shift based on real-time data inputs. You can combine this with `query_cms_items` to pull existing records, analyze them, and adjust the surrounding UI. The agent handles the tedious mapping logic while you monitor the execution trace.

Setup guide

Set up Plasmic (Visual Headless Page 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 Plasmic (Visual Headless Page Builder) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Plasmic (Visual Headless Page 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 Plasmic (Visual Headless Page 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="Plasmic (Visual Headless Page Builder) Agent",
            instructions="You have access to Plasmic (Visual Headless Page 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 Plasmic. 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 Plasmic (Visual Headless Page 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 Plasmic (Visual Headless Page Builder) MCP in OpenAI Agents SDK

Install the openai-agents package. Create an MCPServerStreamableHttp instance pointing to the Vinkius endpoint and pass it to your agent's mcp_servers list. Set cacheToolsList=True to speed up initialization.

Yes. The agent can call publish_cms_item to push draft content live. You can enforce a human-in-the-loop step using OpenAI guardrails before this tool executes.

The SDK catches the error and feeds it back to the agent. The agent can then retry the update_cms_item call with corrected parameters based on the error message.

The MCP standard handles the schema discovery automatically. Your agent knows exactly what count_cms_items requires without you writing manual API wrappers or mapping validation rules.

The query_cms_items tool accesses your CMS records, which may contain proprietary marketing copy or user data. The Vinkius V8 Isolate Sandbox processes these requests ephemerally, ensuring no persistent local storage of your database contents occurs outside the immediate transaction.

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