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

Q: Can I restrict which tools the Gemini agent can use?

Yes. You can apply a toolnames filter when configuring the toolset. This prevents the agent from calling destructive tools like deletecmsitem while still allowing read access.

Q: Does Plasmic (Visual Headless Page Builder) work with Google ADK long-context models?

Yes. The getmodel output can be massive for complex sites. Gemini handles these large JSON trees easily, letting it analyze full project architectures in a single prompt.

Q: How do I test layout changes before publishing with Plasmic (Visual Headless Page Builder) and Google ADK?

You can instruct the agent to use createcmsitem to build drafts. It can then fetch the preview structure using renderhtml before anyone manually clicks publish.

Q: What privacy guarantees exist for my project data?

Tools like getmodel expose your exact component tree and internal site architecture. The underlying MCP connection operates on a zero-trust model, meaning tokens are verified per request and no structural blueprints are retained after the session closes.

Connect Plasmic (Visual Headless Page Builder) to Google ADK to generate and update layouts using Gemini's massive context window.

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 Google ADK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Deep Context Page Analysis

The `get_model` tool feeds the entire SDUI JSON representation of your project element tree into Gemini's 1M+ token context window. Your agent can read the entire site structure at once, mapping dependencies across hundreds of components without losing the thread. You can pipe BigQuery analytics data into the same context, asking the agent to correlate low-performing pages with their exact structural elements. The agent then understands precisely which layouts need revision.

Automated CMS Management via MCP Server

Tools like `query_cms_items` and `count_cms_items` allow your Google ADK agent to audit your entire Plasmic content database. It pulls the records, cross-references them with Vertex AI classification models, and identifies outdated copy. Once identified, the agent runs `update_cms_item` to push new text generated by Gemini. You avoid building custom ETL pipelines just to sync marketing text between your data warehouse and your frontend builder.

Batch Component Generation

The `update_project` tool gives your Gemini agent write access to the visual builder. It can ingest a massive document from Google Drive and programmatically generate corresponding landing page structures. It validates the output by calling `render_html` to check the generated HTML payload. If the markup looks wrong, the agent adjusts the project parameters and tries again, automating the tedious parts of site migrations.

Setup guide

Set up Plasmic (Visual Headless Page Builder) MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Plasmic (Visual Headless Page Builder) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Plasmic (Visual Headless Page Builder)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Plasmic (Visual Headless Page Builder) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install google-adk via pip. Initialize an McpToolset using StreamableHttpServerParameters with your Vinkius URL, then pass it to your LlmAgent in the tools array.

Yes. You can apply a tool_names filter when configuring the toolset. This prevents the agent from calling destructive tools like delete_cms_item while still allowing read access.

Yes. The get_model output can be massive for complex sites. Gemini handles these large JSON trees easily, letting it analyze full project architectures in a single prompt.

You can instruct the agent to use create_cms_item to build drafts. It can then fetch the preview structure using render_html before anyone manually clicks publish.

Tools like get_model expose your exact component tree and internal site architecture. The underlying MCP connection operates on a zero-trust model, meaning tokens are verified per request and no structural blueprints are retained after the session closes.

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