How to Use the Midjourney MCP in VS Code Copilot

Q: Can VS Code Copilot track active Midjourney image jobs?

Yes, your VS Code Copilot agent uses gettaskstatus to check the progress of your image generation. It will inform you in the chat panel when the rendering reaches completion.

Feed Midjourney image assets directly to your VS Code Copilot agent to generate visual assets for your team repository.

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 VS Code Copilot

Create your Vinkius account to connect Midjourney to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate asset generation inside VS Code Copilot

Commit your asset requirements to your repository and let your VS Code Copilot agent run `imagine` to generate them. The entire team can share this configuration via the committed project settings. This MCP Server enables the agent to check the generation status with `get_task_status`. It automatically retrieves the final high-resolution assets and populates your workspace folders.

Edit and upscale images using team-shared tools

Select an image in your project and ask VS Code Copilot to run `describe` to document its design parameters using these MCP tools. This ensures your team maintains visual consistency across different developers and asset batches. Refine your visual outputs using `inpaint` to alter specific regions of an image. If the team needs a different direction, trigger `reroll` to generate a fresh set of four variations within your active editor.

Blend visual styles directly in VS Code Copilot

Combine design mockups by calling `blend` on multiple local image paths. Your VS Code Copilot agent manages the asset transport and feeds the combined output back into your current branch. Keep track of all active design runs using `get_tasks` to list recent jobs. From there, your agent can call `upscale` to fetch the high-resolution versions of your chosen design directions.

Setup guide

Set up Midjourney MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Midjourney MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Midjourney tools listed. Try asking: "List my recent Midjourney transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "midjourney-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 VS Code Copilot

Create a .vscode/mcp.json file in your project root and commit it to your Git repository. Every developer using VS Code Copilot on your team will instantly have access to the same tools.

Yes, your VS Code Copilot agent uses `get_task_status` to check the progress of your image generation. It will inform you in the chat panel when the rendering reaches completion.

The MCP Server uses a single API endpoint managed through Vinkius. Your VS Code Copilot agent routes all calls through this endpoint, allowing your entire team to share the configured API pool.

Ask your agent to upscale a specific quadrant of your generated grid. The agent calls `upscale` using the parent task ID and outputs the high-resolution image URL.

Yes, all prompt data and image task metadata are processed inside an ephemeral, zero-trust sandbox. The server does not persist your team's proprietary prompts or generated image URLs beyond the active 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