How to Use the Hive AI MCP in OpenAI Agents SDK

Q: How do I configure Hive AI tools inside the OpenAI Agents SDK?

You register the MCP server using the MCPServerStreamableHttp helper and pass it to the OpenAI Agent constructor. The SDK auto-discovers endpoints like moderatetext and exposes them to your agent without manual JSON schema mapping.

Q: Can an OpenAI Agents SDK agent run async video moderation with Hive AI?

Yes, the OpenAI agent can call moderatevideoasync to start the background job. It tracks progress using getasynctaskstatus and retrieves results via getasynctaskresult without blocking the main agent loop.

Q: How does Hive AI handle AI-generated content detection in OpenAI Agents SDK?

Your OpenAI agent invokes detectaigeneratedtext or detectaigeneratedimage on incoming user inputs. The tool returns a confidence score that your OpenAI agent evaluates against your custom safety thresholds.

Q: What models are available to my OpenAI agent?

Your OpenAI agent can query listavailablemodels to check which specific classification models are enabled on your account. You can also call getprojectdetails to inspect your active configuration at runtime.

Run safe production agents with the OpenAI Agents SDK by auto-discovering Hive AI tools to block toxic uploads and AI spam instantly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hive AI MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Content Guardrails in OpenAI Agents SDK

This MCP Server exposes `moderate_text` and `moderate_image` directly to your OpenAI agent loops. The SDK handles the tool routing behind the scenes, letting your specialized agents pass moderation tasks to each other during runtime execution. If a user tries to upload an image, your OpenAI agent runs `moderate_image` to check for violations instantly. You get clean, categorized moderation labels directly inside your OpenAI developer dashboard, giving you a clear trace of why an agent blocked a specific file.

Catch Generative Spam in Production Loops

Identify synthetic media instantly by exposing this MCP Server's `detect_ai_generated_text` and `detect_ai_generated_image` tools to your OpenAI Agents SDK. Your OpenAI agent evaluates the output probability score and decides whether to halt the run or request human review. You configure this by passing the streamable HTTP endpoint into the OpenAI Agent constructor. Your agent queries `detect_ai_generated_text` on incoming comments, allowing you to intercept bulk-generated marketing copy before it hits your production vector database.

Handle Heavy Media via Async Pipelines

This MCP server provides `moderate_video_async` and `moderate_audio_async` to handle heavy media files without blocking your OpenAI Agents SDK execution threads. Your agent initiates the task, receives a tracking ID, and executes other logic while the file processes. The OpenAI agent regularly checks the status using `get_async_task_status` and pulls the final payload with `get_async_task_result` once ready. This prevents long-running HTTP connections from blocking your agent handoffs or blowing up your execution budget.

Setup guide

Set up Hive 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 Hive AI tools at runtime.
3

Create your Agent

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

You register the MCP server using the `MCPServerStreamableHttp` helper and pass it to the OpenAI Agent constructor. The SDK auto-discovers endpoints like `moderate_text` and exposes them to your agent without manual JSON schema mapping.

Yes, the OpenAI agent can call `moderate_video_async` to start the background job. It tracks progress using `get_async_task_status` and retrieves results via `get_async_task_result` without blocking the main agent loop.

Your OpenAI agent invokes `detect_ai_generated_text` or `detect_ai_generated_image` on incoming user inputs. The tool returns a confidence score that your OpenAI agent evaluates against your custom safety thresholds.

Your OpenAI agent can query `list_available_models` to check which specific classification models are enabled on your account. You can also call `get_project_details` to inspect your active configuration at runtime.

All text, images, audio, and video content moderation data sent via the tools goes through isolated Vinkius sandboxes. Your API keys are encrypted at rest, and the actual media files are processed securely by Hive AI without persistent storage on the gateway.

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