How to Use the Midjourney MCP in Google ADK

Q: How does Google ADK handle Midjourney task polling?

Your agent receives a task ID from imagine and must use a loop to check gettaskstatus. Because Gemini has a large context window, it can easily track the history of these status updates over time.

Feed Midjourney assets directly into Gemini's long-context window using Google ADK to analyze and generate enterprise-grade visuals.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Midjourney MCP to Google ADK

Create your Vinkius account to connect Midjourney to Google ADK 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 Midjourney with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyzing visual styles inside Google ADK

The `describe` tool lets your Google ADK agent analyze visual assets and convert them into Midjourney text prompts that can be stored in BigQuery. Gemini's massive token capacity inside Google ADK allows your agent to analyze vast amounts of visual data at once. This lets you build a searchable repository of prompt templates that match your corporate style guide. Your Google ADK agent can retrieve these templates later to feed consistent parameters into the generation tool.

Enterprise image generation via Google ADK MCP Server

The `imagine` tool exposes text-to-image capabilities directly to your Google ADK agent, allowing it to draft Midjourney assets based on real-time database updates. Connecting your design workflows to Google Cloud infrastructure makes scaling simple. Your Google ADK agent handles the API calls, monitors progress via `get_task_status`, and writes the final image URLs back to your database. You can trigger generations automatically when new rows appear in BigQuery.

Refining assets with long-context reasoning

The `get_tasks` tool pulls a history of recent generations so your Google ADK agent can use Gemini's long-context reasoning to choose assets for refinement. Gemini excels at comparing multiple options over long conversations in Google ADK. Because the model retains the full context of previous iterations, it makes smarter decisions about which variations to upscale. It can pinpoint the exact image ID to pass to `upscale` based on your original criteria.

Setup guide

Set up Midjourney 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 Midjourney 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="Midjourney_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Midjourney 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 Midjourney. 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 Midjourney 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 Midjourney MCP in Google ADK

Yes, your Google ADK agent can capture the completed image URL from `get_task_status` and write it to a BigQuery table. This lets you build automated datasets of generated visual assets.

You can use the optional tool name filter when initializing your `McpToolset` in Python. This prevents your Google ADK agent from calling expensive tools like `blend` if you only want it to read tasks.

Your agent receives a task ID from `imagine` and must use a loop to check `get_task_status`. Because Gemini has a large context window, it can easily track the history of these status updates over time.

It uses the MCP streamable HTTP transport managed by Vinkius, which handles all authentication under the hood. You only need to pass your single endpoint token to the Google ADK toolset configuration.

Yes, all prompt strings and generated image URLs are processed inside a secure V8 sandbox. The MCP Server runs in an ephemeral container, ensuring no third party can access your visual assets or prompt history.

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