How to Use the Midjourney AI (Generative Image Arts) MCP in OpenAI Agents SDK

Q: How do I configure Midjourney AI (Generative Image Arts) within the OpenAI Agents SDK?

Install the package with pip install openai-agents and initialize MCPServerStreamableHttp with your Vinkius endpoint. Pass this server instance into your Agent constructor using the mcpservers parameter to auto-discover the image generation tools.

Q: How do I rerun a prompt that failed to produce the right style?

Use the rerolljob tool to execute the identical prompt arguments again. This generates a completely new set of four images from the same parameters without rewriting the prompt.

Get raw Midjourney image generation inside your OpenAI Agents SDK pipelines with zero-config tool discovery and real-time tracing.

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 OpenAI Agents SDK

Create your Vinkius account to connect Midjourney AI (Generative Image Arts) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run `generate_image` via OpenAI Agents SDK safely

The `generate_image` tool initiates raw image generation from text prompts directly inside your Python agent workflows. Your agent passes the prompt, receives a Job ID, and uses `get_job` to monitor the render progress until it completes. Built-in guardrails in the OpenAI Agents SDK validate these prompt parameters before sending them to the MCP Server. This prevents your agent from wasting GPU minutes on malformed prompts or invalid aspect ratios.

Multi-agent canvas edits using `pan_image`

The `pan_image` tool lets specialized graphic-agent handoffs shift the view directionally to extend your composition boundaries. One agent can generate the base grid, while a specialized editing agent takes the Job ID to pan or zoom. You can trace these multi-agent handoffs in your OpenAI dashboard to see exactly when the `zoom_out_image` or `pan_image` tools were executed. This setup keeps your creative pipeline organized without manual code intervention.

Extract assets with `upscale_image` and `blend_images`

The `upscale_image` tool extracts a single high-resolution tile from a 2x2 grid generated by your previous runs. Your agent reads the grid, selects the index, and polls `get_job` to retrieve the final asset URL. For complex compositions, your agent can pass multiple URLs to `blend_images` to merge them into a single file. The OpenAI Agents SDK manages these tool calls natively, making image manipulation a core part of your agent's capability toolkit.

Setup guide

Set up Midjourney AI (Generative Image Arts) 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 Midjourney AI (Generative Image Arts) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Midjourney AI (Generative Image Arts) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Midjourney AI (Generative Image Arts) 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="Midjourney AI (Generative Image Arts) Agent",
            instructions="You have access to Midjourney AI (Generative Image Arts) 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 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 OpenAI Agents SDK

Install the package with `pip install openai-agents` and initialize `MCPServerStreamableHttp` with your Vinkius endpoint. Pass this server instance into your Agent constructor using the `mcp_servers` parameter to auto-discover the image generation tools.

Yes, the SDK manages asynchronous polling natively. Your agent calls `generate_image` to get a Job ID, then periodically calls `get_job` to check the progress without blocking the main execution thread.

It uses built-in guardrails to validate prompt arguments before invoking the MCP Server. This ensures invalid parameters are caught locally, saving your subscription from failed generation attempts.

Use the `reroll_job` tool to execute the identical prompt arguments again. This generates a completely new set of four images from the same parameters without rewriting the prompt.

All prompt strings and image URLs pass through an isolated V8 sandbox on Vinkius. Nothing is cached on our servers, and your credentials are encrypted end-to-end to prevent unauthorized access to your generation 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