How to Use the Plasmic (Visual Headless Page Builder) MCP in AutoGen

Q: How do AutoGen agents connect to Plasmic (Visual Headless Page Builder)?

Initialize mcpservertools using StreamableHttpServerParams with your Vinkius URL. Pass the returned list into your AssistantAgent constructor.

Q: Can multiple AutoGen agents use Plasmic (Visual Headless Page Builder) tools simultaneously?

Yes. The McpToolAdapter converts the tool schemas so any agent in the chat group can call renderhtml or updatecmsitem when it has the floor.

Q: How do I prevent AutoGen from deleting the wrong CMS items?

Restrict the deletecmsitem tool to a specific execution agent. Require a human-in-the-loop approval step before that agent is allowed to finalize the deletion.

Q: Do the agents understand the Plasmic JSON structure natively?

They read the raw output from getmodel. You should provide a system prompt explaining the SDUI schema so the agents know how to navigate the element tree properly.

Deploy AutoGen agent teams to debate, review, and execute Plasmic page updates autonomously.

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 AutoGen

Create your Vinkius account to connect Plasmic (Visual Headless Page Builder) to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-Agent Content Review

This MCP Server enables AutoGen teams to manage your Plasmic CMS through structured debate. A writer agent drafts new copy and stages it using `create_cms_item`. An editor agent immediately pulls the draft via `query_cms_items` to review the tone. If the editor rejects the draft, it instructs the writer to revise. Once both agents reach consensus, a publisher agent executes `publish_cms_item` to push it live.

Negotiate Plasmic MCP Server Layouts

You can build workflows where performance and design agents argue over page weight. The design agent pulls the element tree using `get_model` and proposes adding high-resolution image nodes. The performance agent then uses `render_html` to check the resulting markup size. If the HTML payload exceeds your strict budget, the performance agent vetos the change and forces the design agent to trigger `update_project` with a lighter configuration.

Autonomous Database Maintenance

Assign a maintenance agent to keep your Plasmic headless data clean. The agent runs `count_cms_items` daily to monitor database growth and flags any tables approaching row limits. When it finds outdated promotional banners, the agent proposes deletion. A supervisor agent reviews the IDs, approves the action, and the maintenance agent fires `delete_cms_item` to purge the old records permanently.

Setup guide

Set up Plasmic (Visual Headless Page Builder) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Plasmic (Visual Headless Page Builder) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Plasmic (Visual Headless Page Builder)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Plasmic (Visual Headless Page Builder) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Plasmic (Visual Headless Page Builder)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Plasmic (Visual Headless Page Builder) data")
    print(result.messages[-1].content)

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 AutoGen

Initialize `mcp_server_tools` using `StreamableHttpServerParams` with your Vinkius URL. Pass the returned list into your `AssistantAgent` constructor.

Yes. The `McpToolAdapter` converts the tool schemas so any agent in the chat group can call `render_html` or `update_cms_item` when it has the floor.

Restrict the `delete_cms_item` tool to a specific execution agent. Require a human-in-the-loop approval step before that agent is allowed to finalize the deletion.

They read the raw output from `get_model`. You should provide a system prompt explaining the SDUI schema so the agents know how to navigate the element tree properly.

The connection isolates your CMS text payloads inside a stateless execution environment. Vinkius handles the authentication bridging, ensuring your raw database records never leak into persistent storage outside your AutoGen session.

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