How to Use the Hive AI MCP in AutoGen

Q: How do I equip my AutoGen agents with Hive AI tools?

Use the autogen-extmcp package to import the MCP server tools with your server URL. Pass the resulting tool list to your AutoGen AssistantAgent constructor to give them access.

Q: How do AutoGen agents handle async Hive AI tasks?

One AutoGen agent can initiate the task using moderatevideoasync and share the task ID. Another specialized polling agent can monitor the task status via the MCP connection without blocking the main conversation thread.

Q: How do AutoGen agents see what models my project supports?

Your AutoGen agents can call listavailablemodels to get a real-time list of active models. This lets them dynamically adapt their moderation requests based on what features are enabled in your account.

Let your AutoGen agents debate and reach consensus on safety using the Hive AI MCP Server.

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 AutoGen

Create your Vinkius account to connect Hive AI to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve moderation disputes via AutoGen debate

Build a multi-agent safety board where different AutoGen agents debate content decisions using this MCP Server. One AutoGen agent can call `moderate_text` to check for policy violations, while a second agent evaluates the context of the conversation. They negotiate the final action based on the raw Hive AI API scores. This setup avoids single-point-of-failure decisions in your AutoGen moderation pipeline. By forcing AutoGen agents to discuss the output of `moderate_image` before flagging a user, you reduce false positives and handle edge cases more intelligently.

Verify synthetic media authenticity in agent groups

Assign a dedicated auditor agent in your AutoGen group to check the authenticity of shared files. The AutoGen auditor agent uses `detect_ai_generated_image` and `detect_ai_generated_text` to scan any content produced during the group chat. If an AutoGen agent tries to pass off AI-generated work as human, the auditor flags it. The AutoGen group can then decide whether to reject the contribution or proceed with an explicit warning. This is highly useful for collaborative AutoGen environments where source integrity is critical.

Coordinate asynchronous moderation across agents

When dealing with large files, your AutoGen coordinator agent can spin off tasks using `moderate_video_async` or `moderate_audio_async`. Instead of pausing the entire AutoGen conversation, other agents can continue working on text-based tasks while the background job runs. A watchdog AutoGen agent monitors the task by querying `get_async_task_status`. Once `get_async_task_result` returns the completed payload, the watchdog injects the Hive AI safety verdict back into the group chat for final decision-making.

Setup guide

Set up Hive AI MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Hive AI tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Hive AI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Hive AI data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Hive AI_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Hive AI data")
    print(result.messages[-1].content)

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 AutoGen

Use the autogen-ext[mcp] package to import the MCP server tools with your server URL. Pass the resulting tool list to your AutoGen AssistantAgent constructor to give them access.

Yes, AutoGen agents run independently and can invoke tools like `moderate_text` or `moderate_image` in parallel. The underlying server handles concurrent requests smoothly.

One AutoGen agent can initiate the task using `moderate_video_async` and share the task ID. Another specialized polling agent can monitor the task status via the MCP connection without blocking the main conversation thread.

Your AutoGen agents can call `list_available_models` to get a real-time list of active models. This lets them dynamically adapt their moderation requests based on what features are enabled in your account.

Your video files and image URLs are processed inside a zero-trust, ephemeral V8 sandbox on Vinkius. The MCP Server acts as a secure pass-through directly to Hive, leaving no cached media files or logs behind once the execution completes.

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