How to Use the EyePop.ai MCP in OpenAI Agents SDK

Q: Can I trace EyePop.ai tool calls within the OpenAI Agents SDK dashboard?

Yes. Every execution of analyzeimage or analyzevideo shows up as a standard tool call in your tracing timeline. You get full visibility into payload sizes and response latencies.

Run real-time computer vision pipelines securely inside your production 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 EyePop.ai MCP to OpenAI Agents SDK

Create your Vinkius account to connect EyePop.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 EyePop.ai with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Visual Pipelines in OpenAI Agents SDK

Point your agent to `create_pop` and let it spin up custom visual processing pipelines on the fly. You can query available configurations using the MCP Server tools like `list_pops` or inspect specific pipelines with `get_pop` to ensure the correct models are running. Since OpenAI's framework handles agent handoffs, you can have a supervisor agent inspect the active pipeline before passing the task to a worker agent. Control remains tight because visual pipeline configurations stay locked down while allowing dynamic scaling.

Extract Structured Data from Media

Feed video files or static images directly to your agent to run object detection or face recognition using `analyze_image` or `analyze_video`. Calling these tools extracts structured visual data, coordinates, and labels without writing custom computer vision code. Tracing these tool calls in the OpenAI dashboard gives you a clear view of processing times and token payloads. Slow video analysis becomes easy to debug when you can see exactly which tool invocation caused the bottleneck.

Verify Model Inventory and Connection Status

Keep your agents updated on what models are available by letting them query `list_models` and check specific details with `get_model`. Doing this prevents runtime failures when an agent tries to run an unsupported classification task. Before running heavy video payloads, your agent can execute `check_eyepop_status` to confirm the API connection is active. Guardrails inside your agent configuration can catch connection issues early before they affect production using this MCP integration.

Setup guide

Set up EyePop.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 EyePop.ai tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives EyePop.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 EyePop.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="EyePop.ai Agent",
            instructions="You have access to EyePop.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 EyePop.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 EyePop.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 EyePop.ai MCP in OpenAI Agents SDK

Install the packages and initialize MCPServerStreamableHttp with your Vinkius endpoint. Pass the server instance directly to the Agent constructor in the mcp_servers list.

Yes. Every execution of `analyze_image` or `analyze_video` shows up as a standard tool call in your tracing timeline. You get full visibility into payload sizes and response latencies.

The SDK relies on your agent's built-in error handling and loop limits. You should use `check_eyepop_status` to verify availability before launching intensive analytical tasks.

No system prompts are needed. The agent auto-discovers the MCP tool definitions, allowing it to select `analyze_image` or `list_models` based on the user's plain-text request.

Your media payloads go directly to the sandboxed Vinkius environment. No raw video files or images are stored on the MCP host, keeping your visual data isolated and ephemeral.

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