How to Use the APImage MCP in Google ADK

Q: How do I register APImage tools inside Google ADK?

Use the McpToolset class configured with your Vinkius HTTP URL. Pass this toolset directly into your LlmAgent constructor under the tools parameter to expose the MCP tools to Gemini.

Q: How do I restrict which APImage tools are exposed to Google ADK?

You can pass an optional toolnames filter list to your toolset initialization. This lets you restrict access to heavy operations like inpaintimage while keeping basic tools active.

Q: How do I confirm the APImage connection is live?

Have your agent execute checkapimagestatus at the start of your workflow. This returns a direct diagnostic status to ensure your credentials and endpoints are fully functional.

Deploy enterprise media agents on Google Cloud that generate and modify assets using Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect APImage MCP to Google ADK

Create your Vinkius account to connect APImage 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 APImage with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate assets directly from Google ADK workflows

`generate_image` is the primary tool on this MCP Server that lets your Gemini-powered agent create high-fidelity assets. Your agent uses `list_models` first to discover which generation engines are currently available on the server. Integrating this with your enterprise data pipelines allows you to feed BigQuery row data directly into prompts. Your agent handles the translation from structured data to visual assets autonomously.

Clean and edit visual media using this MCP Server

`remove_background` extracts the main subject of any image by deleting the background layer. After isolation, your agent runs `upscale_image` to prepare the asset for high-resolution marketing campaigns. This pipeline operates within Google Cloud's execution environment. Your agent can run these transformations in batch processes without manual intervention.

Modify localized image regions with Google ADK

`inpaint_image` replaces specific parts of an image using a mask and a new text prompt. If you need to track what was changed, `list_generations` pulls the complete history of your active session. Your agent uses `get_generation` to inspect the metadata of prior runs. This lets the model verify the parameters of successful generations before executing new edits.

Setup guide

Set up APImage 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 APImage 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="APImage_agent",
    model="gemini-2.0-flash",
    instruction="You have access to APImage 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 APImage. 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 APImage 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 APImage MCP in Google ADK

Use the `McpToolset` class configured with your Vinkius HTTP URL. Pass this toolset directly into your `LlmAgent` constructor under the tools parameter to expose the MCP tools to Gemini.

Yes, Gemini's long context window easily tracks editing history. The agent can read an image, run `image_to_image`, and then isolate the subject using `remove_background` in a single session.

You can pass an optional `tool_names` filter list to your toolset initialization. This lets you restrict access to heavy operations like `inpaint_image` while keeping basic tools active.

Have your agent execute `check_apimage_status` at the start of your workflow. This returns a direct diagnostic status to ensure your credentials and endpoints are fully functional.

Every prompt, mask, and generated image is processed within an ephemeral zero-trust MCP environment. Your visual assets are never cached or used for training, keeping your company IP secure.

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