How to Use the Image Router MCP in OpenAI Agents SDK

Q: Can my agent use this MCP Server to edit existing files?

Yes, the agent can call editimage or generatevariation to modify existing assets. It analyzes the input image and applies your text prompts to generate the updated version automatically.

Stop guessing which image model to use. Let your OpenAI Agents SDK automatically route prompts to the best generator.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Image Router MCP to OpenAI Agents SDK

Create your Vinkius account to connect Image Router 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 Image Router with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dynamic routing for OpenAI Agents SDK teams

Your OpenAI Agents SDK agents don't need hardcoded image model endpoints anymore. By exposing the tools of this MCP Server directly to your agent loop, the system analyzes your prompt's style and selects the right engine. You save credits by avoiding overpowered models for simple tasks. When an OpenAI agent receives a specific aesthetic request, it runs `list_styles` to match the design intent. It then triggers `generate_image` using the chosen backend without requiring manual intervention from your developers.

Production-grade generation tracking

Polling for high-resolution assets can stall your OpenAI Agents SDK execution threads. This MCP Server solves that by providing asynchronous status checks through `get_generation_status` directly inside your agent flows. If the initial output needs tweaks, your OpenAI agent calls `edit_image` or `generate_variation` to refine the asset. You get a clean, non-blocking workflow that handles heavy image processing tasks in the background.

Upscaling and validation on the fly

Low-resolution drafts are fine for quick previews, but your OpenAI Agents SDK production pipeline demands high-fidelity assets. The `upscale_image` tool in this MCP configuration lets your agent bump up the quality of any generated asset once the user approves the draft. By querying `get_model` before execution, your OpenAI agent verifies the active parameters and limitations of the target generator. This prevents failed API calls and keeps your automated media pipeline running without human oversight.

Setup guide

Set up Image Router 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 Image Router tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Image Router 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="Image Router Agent",
            instructions="You have access to Image Router 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 Image Router. 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 Image Router 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 Image Router MCP in OpenAI Agents SDK

Install the package using pip, then initialize the server with `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass this instance in the `mcp_servers` list when creating your Agent. Enabling `cacheToolsList` will speed up tool discovery.

Yes, the agent can call `edit_image` or `generate_variation` to modify existing assets. It analyzes the input image and applies your text prompts to generate the updated version automatically.

Instead of blocking the agent thread during long runs, the toolset uses `get_generation_status` to track progress. Your agent can perform other tasks and check back periodically until the asset is ready.

The system handles failovers by checking active endpoints. Your agent can run `check_imagerouter_status` to verify connection health, then fall back to another model from `list_models_by_category` if the primary choice is unresponsive.

All prompt text and image metadata processed by this server are sandboxed in Vinkius's ephemeral V8 isolates. Your source files are never stored or used for training, ensuring complete isolation for your proprietary visual assets.

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