How to Use the imgix (Real-time Image Processing) MCP in OpenAI Agents SDK

Q: How do I register the imgix (Real-time Image Processing) tools with the OpenAI Agents SDK?

Install openai-agents via pip and configure the MCPServerStreamableHttp transport pointing to your Vinkius endpoint. Pass this server instance inside the mcpservers list when instantiating your Agent. The agent automatically discovers tools like purge and getasset at runtime.

Q: Can my OpenAI Agents SDK agent use imgix (Real-time Image Processing) to clean up old distribution points?

Yes, your OpenAI Agents SDK agent can use disablesource to stop serving images from a specific origin, or deletesource to remove it permanently. This is useful for cleaning up staging environments or temporary promotional folders dynamically.

Control your CDN configurations and purge cached images directly from your OpenAI Agents SDK workflows.

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 OpenAI Agents SDK

Create your Vinkius account to connect imgix (Real-time Image Processing) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Programmatic CDN source management

The imgix (Real-time Image Processing) MCP Server lets your OpenAI Agents SDK agent deploy and modify image delivery origins automatically. By using `create_source`, your agent can hook up a new S3 bucket or web folder to the CDN, spinning up a live image-serving domain without manual setup. This imgix toolset handles your CDN configuration lifecycle from inception to decommissioning. If a source is no longer needed, your agent can call `disable_source` or `delete_source` to stop traffic immediately, keeping your infrastructure clean and cost-efficient.

Instant cache purging for OpenAI Agents SDK

This MCP Server exposes direct imgix cache invalidation capabilities to your OpenAI Agents SDK pipelines. When your application updates an original asset, your OpenAI Agents SDK agent triggers `purge` to clear the cached original and all its resized variants across global edge nodes in seconds. Instead of waiting for TTLs to expire, your OpenAI Agents SDK setup uses `purge` to force immediate re-fetches. You can verify the current state of any file using `get_asset` to confirm details like file size and content type before and after the imgix purge occurs.

Live asset discovery and monitoring

Your OpenAI Agents SDK agent can inspect active CDN distribution points using the `list_sources` and `list_assets` tools. This gives your OpenAI Agents SDK agent a real-time view of your image inventory and deployment statuses. When troubleshooting broken images, your OpenAI Agents SDK agent calls `get_source` to inspect the origin connection parameters and deployment state. This telemetry lets your OpenAI Agents SDK agent make smart decisions, like auto-enabling a disabled distribution via `enable_source` when it detects origin traffic.

Setup guide

Set up imgix (Real-time Image Processing) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all imgix (Real-time Image Processing) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives imgix (Real-time Image Processing) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate imgix (Real-time Image Processing) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="imgix (Real-time Image Processing) Agent",
            instructions="You have access to imgix (Real-time Image Processing) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip and configure the `MCPServerStreamableHttp` transport pointing to your Vinkius endpoint. Pass this server instance inside the `mcp_servers` list when instantiating your Agent. The agent automatically discovers tools like `purge` and `get_asset` at runtime.

Yes, your OpenAI Agents SDK agent can use `disable_source` to stop serving images from a specific origin, or `delete_source` to remove it permanently. This is useful for cleaning up staging environments or temporary promotional folders dynamically.

The SDK relies on built-in HTTP handling, but you should configure agent-side loop detection to prevent runaway calls to `purge` or `list_assets`. Setting `cacheToolsList=True` during initialization also reduces redundant schema discovery requests.

You can control tool access using the SDK's built-in guardrails. Before the agent executes a destructive tool like `delete_source`, your guardrail code can intercept the call, validate the source ID, and require human approval.

The server only processes CDN source configurations, asset metadata, and purge URLs. None of your raw image binaries are sent to OpenAI or stored on the Vinkius platform, and all connections are isolated in ephemeral V8 sandboxes.

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