How to Use the GAN.ai MCP in AutoGen

Q: How do I give GAN.ai tools to my AutoGen agents?

Use the mcpservertools function from the AutoGen MCP extension, pointing it to your Vinkius endpoint. This returns a list of callable tools you can directly assign to an AssistantAgent in its constructor.

Q: Can I have one agent generate videos and another check the status?

Yes, that's a perfect use case for AutoGen. You'd have a GeneratorAgent with access to generatepersonalizedvideos and a MonitorAgent with access to getgenerationstatus. They coordinate their work through conversation.

Q: How can AutoGen agents decide which GAN.ai video template is best?

You set up a conversation. A CreativeAgent might call listvideoprojects, and a DataAgent could then call getvideostats for each project to see which performed best historically. They then discuss and agree on which one to use for the new campaign.

Q: Can I create a 'safety' agent for my GAN.ai workflow in AutoGen?

Definitely. You can build a SafetyAgent that has access to verifyapiconnection and getworkspaceinfo. Before any large campaign is run, other agents must get a sign-off from it, ensuring the connection is healthy and you have enough resources.

Let your AutoGen agents debate, plan, and execute personalized video campaigns for you.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GAN.ai MCP to AutoGen

Create your Vinkius account to connect GAN.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 GAN.ai with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble an AI Marketing Team

With AutoGen, you create a team of specialized agents that talk to each other to get things done. A 'CampaignPlanner' agent can use `list_video_projects` to propose a template. A 'QA' agent can then check that template's required inputs with `get_project_metadata` to make sure it's valid. Once they agree, the Planner can instruct an 'Executor' agent to call `generate_personalized_videos`. This isn't one agent following a script; it's a conversation between specialists that leads to a concrete action. It's a more robust way to automate.

Debate Campaign Strategy with AutoGen Agents

The real power here is consensus through debate. Imagine a 'Budget' agent that monitors costs. When another agent wants to run a huge job with `generate_personalized_videos`, the Budget agent can check `get_workspace_info` and push back if it exceeds spending limits. They can then negotiate a smaller batch size or a different approach. A 'Performance' agent might argue for the campaign by showing strong past results from `get_video_stats`. The final decision is a product of this multi-perspective debate, not a single command.

Automate Monitoring and Reporting

You can create an agent whose only job is to monitor campaigns. It periodically calls `get_generation_status` for active jobs. If it finds a failure, it can report the details to a human or a 'Fixer' agent that tries to resolve the issue. Another agent, the 'Analyst,' could be tasked with summarizing performance. At the end of the day, it calls `list_generated_videos` and `get_video_stats` to create a report. This MCP server gives your agent team everything they need to run the entire operation.

Setup guide

Set up GAN.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 GAN.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="GAN.ai_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent GAN.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="GAN.ai_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent GAN.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 GAN.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 GAN.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 GAN.ai MCP in AutoGen

Use the `mcp_server_tools` function from the AutoGen MCP extension, pointing it to your Vinkius endpoint. This returns a list of callable tools you can directly assign to an `AssistantAgent` in its constructor.

Yes, that's a perfect use case for AutoGen. You'd have a `GeneratorAgent` with access to `generate_personalized_videos` and a `MonitorAgent` with access to `get_generation_status`. They coordinate their work through conversation.

You set up a conversation. A `CreativeAgent` might call `list_video_projects`, and a `DataAgent` could then call `get_video_stats` for each project to see which performed best historically. They then discuss and agree on which one to use for the new campaign.

Definitely. You can build a `SafetyAgent` that has access to `verify_api_connection` and `get_workspace_info`. Before any large campaign is run, other agents must get a sign-off from it, ensuring the connection is healthy and you have enough resources.

The server processes variables needed for video rendering, like names or account details, that you pass into tools like `generate_personalized_videos`. Vinkius ensures security by running every tool call in a fresh, ephemeral container. The MCP server is stateless and doesn't retain your personalization data after the job is done.

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