How to Use the Midjourney AI (Generative Image Arts) MCP in Google ADK

Q: How do I set up Midjourney AI (Generative Image Arts) with the Google ADK?

Install the package via pip install google-adk and configure McpToolset with your Vinkius HTTP endpoint. Pass this toolset directly to your LlmAgent to expose the generation tools to Gemini.

Q: Can I limit which Midjourney AI (Generative Image Arts) tools Google ADK can access?

Yes, you can use the toolnames filter in your McpToolset configuration to restrict access. For example, you can expose only generateimage and upscaleimage while hiding administrative tools.

Q: How does Google ADK handle Midjourney AI (Generative Image Arts) job polling?

The agent calls generateimage to start a job, retrieves the Job ID, and then uses a polling loop with getjob. Gemini's long-context window keeps track of the job state across long conversation turns.

Q: How can I combine multiple reference images using this setup?

Use the blendimages tool by passing a comma-separated list of image URLs. The server will merge the compositions into a new grid, which your agent can then process.

Connect Midjourney AI (Generative Image Arts) to Google ADK to generate visual assets directly from your BigQuery data pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Midjourney AI (Generative Image Arts) MCP to Google ADK

Create your Vinkius account to connect Midjourney AI (Generative Image Arts) 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 AI (Generative Image Arts) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger `generate_image` from BigQuery data using Google ADK

The `generate_image` tool takes text prompts generated from your Google Cloud databases and turns them into high-fidelity images. Your Gemini agent reads product descriptions from BigQuery, formats the prompt, and runs the generation. Because the Google ADK handles long-context reasoning, it can analyze thousands of rows of product data to generate highly specific style prompts before sending them to the MCP Server.

Reverse engineer assets with `describe_image`

The `describe_image` tool analyzes an input image and outputs the exact text prompts needed to recreate its style in Midjourney. Your Gemini agent can read these descriptions and store them directly back into Google Cloud Storage. This lets you build automated style catalogs. Your agent uses the ADK's native tools to process the output, making it easy to index visual styles alongside your enterprise data.

Refine grids using `upscale_image` and `pan_image`

The `upscale_image` tool isolates a specific quadrant from your 2x2 grid and scales it to print resolution. Your agent monitors this process asynchronously via the `get_job` endpoint. Once upscaled, you can use `pan_image` to extend the canvas borders in any direction. The Google ADK handles these sequential steps, letting you build complex visual workflows on top of Google Cloud infrastructure.

Setup guide

Set up Midjourney AI (Generative Image Arts) 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 AI (Generative Image Arts) 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 AI (Generative Image Arts)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Midjourney AI (Generative Image Arts) 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 AI (Generative Image Arts) 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 AI (Generative Image Arts) MCP in Google ADK

Install the package via `pip install google-adk` and configure `McpToolset` with your Vinkius HTTP endpoint. Pass this toolset directly to your `LlmAgent` to expose the generation tools to Gemini.

Yes, you can use the `tool_names` filter in your `McpToolset` configuration to restrict access. For example, you can expose only `generate_image` and `upscale_image` while hiding administrative tools.

The agent calls `generate_image` to start a job, retrieves the Job ID, and then uses a polling loop with `get_job`. Gemini's long-context window keeps track of the job state across long conversation turns.

Use the `blend_images` tool by passing a comma-separated list of image URLs. The server will merge the compositions into a new grid, which your agent can then process.

Your source URLs and prompt text are processed inside ephemeral, zero-trust V8 isolates. Vinkius handles the authentication tokens securely, ensuring your Google Cloud data and generated assets never leak to public logs.

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