How to Use the Cloudinary MCP in OpenAI Agents SDK

Q: How do I perform bulk tasks in Cloudinary using OpenAI Agents SDK?

Loop through your media list using listmediaresources. You can then pass individual identifiers to other tools to perform batch operations safely.

Manage your Cloudinary media assets directly inside your OpenAI Agents SDK production pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cloudinary MCP to OpenAI Agents SDK

Create your Vinkius account to connect Cloudinary 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 Cloudinary with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Full asset control in OpenAI Agents SDK

Handle your media library without leaving your Python code. You can trigger `delete_media_resource` to clean up old files or use `search_media_library` to find specific assets instantly. Everything happens inside your agent's execution loop. Your production agent verifies every call against your safety constraints before touching your cloud storage.

Monitor Cloudinary usage programmatically

Keep an eye on your storage and bandwidth quotas through `get_cloudinary_usage_report`. It gives you the raw numbers you need to adjust your scaling logic. Your OpenAI agents receive this data as structured objects. You avoid hidden costs by checking your limits before running high-volume transformation batches.

Automate Cloudinary media workflows

Call `list_media_transformations` or `list_upload_presets` to understand how your assets are processed. Your agent builds a map of existing logic to prevent duplicate work. This MCP server makes it easy to query your setup. Your code stays clean because you aren't hardcoding configuration strings into your agent logic.

Setup guide

Set up Cloudinary 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 Cloudinary tools at runtime.
3

Create your Agent

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

Run the agent

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

You connect the server via the MCPServerStreamableHttp class. Once the agent constructor loads the tools, your code calls them like native functions.

Yes, you can manually whitelist the functions you want to expose. This keeps your agent's tool-calling surface area minimal and secure.

The SDK provides full tracing for every tool invocation. If a request fails, you see the exact error output in your dashboard logs.

Loop through your media list using `list_media_resources`. You can then pass individual identifiers to other tools to perform batch operations safely.

Your media metadata and account credentials stay isolated in our V8 sandbox. The agent only receives the specific responses requested during its execution.

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