How to Use the Claid AI MCP in OpenAI Agents SDK

Q: Can I track image processing costs with my Claid AI and OpenAI Agents SDK integration?

Yes. Your agent can use the getclaidaccountinfo tool. This gives it direct access to your account balance and API quotas so it can make decisions before running expensive operations.

Process e-commerce images and check account status using the OpenAI Agents SDK and Claid AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Claid AI MCP to OpenAI Agents SDK

Create your Vinkius account to connect Claid AI 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 Claid AI with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Edit Images with a Single Command

The `enhance_image` tool lets your OpenAI Agent run multiple edits at once. Instead of separate calls for upscaling and background removal, you can chain them into a single operation. This is perfect for building production agents that need to prep product photos efficiently. Your agent can also use `upscale_image_resolution` for high-res outputs or `remove_image_background` for clean cutouts. Because the OpenAI Agents SDK has built-in guardrails, you can trace every image operation and ensure the agent only performs approved edits.

Manage Claid AI from your OpenAI Agent

This isn't just about images. Give your agent the `get_claid_account_info` tool to monitor your usage and quotas. It can check your balance before starting a large batch of edits. You can also manage async jobs. If an image enhancement takes time, your agent can use `get_processing_task_details` to poll for the result. This MCP Server makes your agent aware of its own resources and state.

Discover Operations and Webhooks

Your agent doesn't need to guess what it can do. The `list_available_ai_operations` tool returns a current list of all possible image edits supported by the Claid API. It's a simple way to make your agent adaptable. For more complex workflows, the agent can check configured webhooks with `list_claid_webhooks`. This helps your agent understand how it will be notified when asynchronous tasks are complete, which is critical for building reliable systems with the OpenAI Agents SDK.

Setup guide

Set up Claid AI 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 Claid AI tools at runtime.
3

Create your Agent

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

Run the agent

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

You connect the Claid AI MCP Server to your agent with a single URL. The OpenAI Agents SDK automatically discovers the tools, like `enhance_image`, letting your agent edit photos or check account status without any extra code.

Yes. Your agent can use the `get_claid_account_info` tool. This gives it direct access to your account balance and API quotas so it can make decisions before running expensive operations.

You can process any product photos or user-generated images. The tools are built for e-commerce tasks like removing backgrounds with `remove_image_background` or improving quality with `upscale_image_resolution`.

No, it's straightforward. You just pass the Vinkius MCP Server endpoint to the `MCPServerStreamableHttp` constructor in your Python code. The agent framework handles the rest.

Vinkius processes your image data in an ephemeral, sandboxed environment for each request. Authentication is handled by your single endpoint token, and the server itself doesn't store your images after the job is done. It's a zero-trust model.

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