How to Use the imgix (Real-time Image Processing) MCP in Google ADK

Q: How do I connect the imgix (Real-time Image Processing) server to my Google ADK agent?

Instantiate an McpToolset using the StreamableHttpServerParameters pointing to your Vinkius URL. Pass this toolset into your LlmAgent constructor to expose tools like purge and listassets to Gemini.

Q: Can I limit my Google ADK agent to only purge images using the imgix (Real-time Image Processing) tools?

Yes, you can use the toolnames filter when initializing your McpToolset. By specifying only purge and getasset, you prevent the agent from accidentally calling destructive tools like deletesource.

Q: How does the agent handle offline CDN sources?

When getsource returns a disabled status, your agent can evaluate the failure and call enablesource to restore image delivery. This self-healing logic keeps your cloud infrastructure running smoothly.

Manage your CDN origins and invalidations directly within your Google ADK agent pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect imgix (Real-time Image Processing) MCP to Google ADK

Create your Vinkius account to connect imgix (Real-time Image Processing) 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 imgix (Real-time Image Processing) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated CDN provisioning via Google ADK

The imgix (Real-time Image Processing) MCP Server gives your Gemini models direct control over your image delivery architecture. By exposing the `create_source` tool, your Google ADK agent can register new storage buckets as CDN origins based on data pulled from BigQuery. Your Google ADK agent monitors these connections using `get_source` to verify deployment statuses. If a cloud storage bucket changes, your Google ADK agent updates the CDN origin settings on the fly with `update_source` to prevent broken image links.

Real-time cache invalidation and audits

This MCP Server enables your Google ADK agent to clean up stale CDN assets instantly. When a database record updates in Vertex AI, your Google ADK agent calls `purge` to wipe the cached asset and all its processed variations from the edge. To verify the cleanup worked, your Google ADK agent uses `get_asset` to retrieve the latest file metadata. This ensures your front-end applications connected to Gemini never display outdated product images or broken files.

Bulk asset discovery and status checks

Your Google ADK agent can scan entire image distributions using `list_assets` and `list_sources`. This allows your Google ADK pipeline to audit active CDN domains and flag inactive setups. If your Google ADK agent finds an origin that was accidentally turned off, it uses `enable_source` to bring the distribution back online. This automated recovery keeps your Google ADK media pipelines active without requiring manual DevOps intervention.

Setup guide

Set up imgix (Real-time Image Processing) 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 imgix (Real-time Image Processing) 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="imgix (Real-time Image Processing)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to imgix (Real-time Image Processing) 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 imgix. 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 imgix (Real-time Image Processing) 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 imgix (Real-time Image Processing) MCP in Google ADK

Instantiate an `McpToolset` using the `StreamableHttpServerParameters` pointing to your Vinkius URL. Pass this toolset into your `LlmAgent` constructor to expose tools like `purge` and `list_assets` to Gemini.

Yes, you can use the `tool_names` filter when initializing your `McpToolset`. By specifying only `purge` and `get_asset`, you prevent the agent from accidentally calling destructive tools like `delete_source`.

Yes, the 1M+ token limit of Gemini models lets your Google ADK agent analyze the massive JSON lists returned by `list_assets` and `list_sources` in a single pass. This is perfect for complex inventory audits and sync checks.

When `get_source` returns a disabled status, your agent can evaluate the failure and call `enable_source` to restore image delivery. This self-healing logic keeps your cloud infrastructure running smoothly.

Vinkius runs this MCP Server in a zero-trust, ephemeral sandbox environment. Your imgix API credentials and CDN purge requests are never logged or stored, ensuring your asset metadata remains completely private.

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