How to Use the Adobe Firefly MCP in VS Code Copilot

Q: How do we enable Adobe Firefly for our team in VS Code Copilot?

A team lead or admin should create a .vscode/mcp.json file in the project's root. Add the Vinkius MCP server URL to that file and commit it to your Git repository. Everyone on the team will automatically get the tools.

Q: Can we control which Adobe Firefly models are used by VS Code Copilot?

Yes. The texttoimage tool lets you specify which model to use. You can instruct your Copilot agent to use a specific model for photorealism or artistic style when it makes the call. Use listmodels to see your options.

Q: What's the best way to use the Adobe Firefly tools with VS Code Copilot for web development?

Have your agent generate assets like SVGs with texttovector and save them to your project's asset directory. Then, you can ask Copilot to write the HTML or React component code to import and display that new asset. It closes the loop between asset creation and implementation.

Give your entire engineering team access to Adobe Firefly's generative tools inside VS Code Copilot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Adobe Firefly MCP to VS Code Copilot

Create your Vinkius account to connect Adobe Firefly 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 Adobe Firefly with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Team-Wide Access to Firefly Tools

Add this MCP server to your project's `.vscode/mcp.json` file and commit it. Now, every developer on your team who pulls the repo gets the same set of Adobe Firefly tools in their VS Code Copilot instance. No individual setup required. Your team's agent can now run `text_to_image` to generate placeholder graphics or `text_to_vector` for icons, ensuring visual consistency across the project. It's a shared capability, managed in one place.

Generative Editing in Your Editor

This isn't just about creating new assets. Your Copilot agent can use tools to modify existing images. Use `remove_background` to prep product photos or `generative_expand` to change an image's aspect ratio to fit a new layout. For detailed fixes, the `generative_fill` tool is perfect. Just tell your agent what part of the image to change and what to put there instead. You can iterate on creative assets right inside VS Code, keeping your workflow in one window.

A Secure MCP Server for Your Team

Vinkius manages the server infrastructure, so you don't have to. This MCP server provides a single, secure endpoint for your whole team to connect VS Code Copilot to Adobe Firefly. It's SOC 2 compliant and ready for enterprise use. Your agent can call any of the ten available tools, from `generate_object` for complex composites to `text_effects` for styled headlines. The setup is simple, and the connection is reliable.

Setup guide

Set up Adobe Firefly 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 Adobe Firefly 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 Adobe Firefly tools listed. Try asking: "List my recent Adobe Firefly transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "adobe-firefly-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 Adobe Firefly. 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 Adobe Firefly 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 Adobe Firefly MCP in VS Code Copilot

A team lead or admin should create a `.vscode/mcp.json` file in the project's root. Add the Vinkius MCP server URL to that file and commit it to your Git repository. Everyone on the team will automatically get the tools.

Yes. The `text_to_image` tool lets you specify which model to use. You can instruct your Copilot agent to use a specific model for photorealism or artistic style when it makes the call. Use `list_models` to see your options.

Have your agent generate assets like SVGs with `text_to_vector` and save them to your project's asset directory. Then, you can ask Copilot to write the HTML or React component code to import and display that new asset. It closes the loop between asset creation and implementation.

No. This Vinkius-hosted MCP server provides the connection between VS Code Copilot and the Adobe Firefly API. You still need an Adobe account with API access to pay for the actual image generation compute.

All data, including your text prompts and any image files you upload, is passed through an encrypted, short-lived environment on its way to the Adobe API. Vinkius does not inspect or retain any of this data. Your intellectual property is processed securely and then deleted.

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