How to Use the Adobe Firefly MCP in Google ADK

Q: How do I add Adobe Firefly tools to my Google ADK agent?

You'll use the McpToolset from the Google ADK library, pointing it to your Vinkius server URL. Then, you just pass that toolset into your LlmAgent's tools parameter during initialization.

Connect Google ADK agents to Adobe Firefly and generate creative assets based on your data in BigQuery.

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 Google ADK

Create your Vinkius account to connect Adobe Firefly 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 Adobe Firefly with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn BigQuery Insights into Images

Your Gemini agent can now turn data into creative assets. Let it analyze sales trends in BigQuery, formulate a marketing angle, and then use the `text_to_image` tool to generate ad creative based on its findings. This isn't just a chatbot. It's an agent that connects your enterprise data directly to a powerful image generation engine. It can even use `text_to_vector` to create logos or icons that match the data story.

Complex, Long-Context Image Workflows

A Gemini agent's huge context window changes the game for image editing. Your agent can hold a complex, multi-step plan in its head without getting lost. For example, it can `upload_image`, then decide to `generative_expand` it to a new size, and finally use `generative_fill` to add new elements. This is a big step up from simple one-shot commands. The agent can reason about a sequence of edits, making it possible to automate sophisticated creative tasks that used to require manual work.

Firefly Tools Native to Your Google Agent

The `McpToolset` makes this Adobe Firefly MCP Server feel like a native part of the Google Cloud ecosystem. Your agent can call `remove_background` or apply `text_effects` with the same syntax it uses to interact with a Vertex AI service. There's no awkward translation layer. You add the toolset, and your agent gains ten new creative abilities. You can even use the `tool_names` filter to expose only a specific subset of Firefly tools to a particular agent, giving you fine-grained control within your GCP environment.

Setup guide

Set up Adobe Firefly 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 Adobe Firefly 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="Adobe Firefly_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Adobe Firefly 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 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 Google ADK

You'll use the `McpToolset` from the Google ADK library, pointing it to your Vinkius server URL. Then, you just pass that toolset into your LlmAgent's `tools` parameter during initialization.

Yes, absolutely. An agent built with Google ADK can use the `text_to_image` tool to generate pictures, then use other tools to insert them into a new Google Slides presentation, all as part of one automated workflow.

You can automate things like generating product shots from descriptions in a database, creating social media images from a content calendar in Google Sheets, or producing vector icons with `text_to_vector` for your internal apps.

The MCP Server uses a separate Vinkius endpoint token for access. Your Google ADK agent, running in your GCP project, will use this token to securely connect to the managed server.

Your prompts and image data are sent to the Vinkius-managed MCP Server for processing. Each server runs in a zero-trust sandbox that is destroyed after the request, so your proprietary data isn't stored. It's a direct, secure channel between your agent and the Firefly API.

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