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

Q: Can the OpenAI Agents SDK track GAN.ai video engagement?

Yes. Your agent calls getvideostats to read open and play rates. You can pipe that data directly into a specialized analytics agent.

Q: How do I list available GAN.ai landing pages using the OpenAI Agents SDK?

The agent invokes listlandingtemplates. It returns the exact template IDs required for your campaign. Set cacheToolsList=True to speed up the tool discovery phase.

Q: Does this MCP setup support single video generation?

It does. The agent triggers generatesinglevideo for one-off requests. It handles the parameters natively without manual mapping.

Build safe, traceable video marketing agents with GAN.ai and the OpenAI Agents SDK.

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 OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Bulk Video Generation via MCP Server

Your OpenAI agent calls `generate_personalized_videos` to spin up thousands of targeted videos at once. It pulls the base template right from `list_video_projects` and maps your recipient data to the variables. You do not have to write custom batching logic. If a specific high-value prospect needs a custom touch, the agent shifts to `generate_single_video`. The SDK built-in guardrails ensure the agent validates the payload before hitting the GAN.ai endpoint. You keep the execution safe while scaling outbound campaigns.

Track Production Rendering Jobs

The `get_generation_status` tool lets your agent poll the exact state of any video batch so it knows when a render finishes. It checks the queue without hallucinating completion times. Once the video is ready, the agent grabs the URL using `get_video_metadata`. It then pulls engagement metrics through `get_video_stats` to see if the prospect actually clicked play. You get full tracing in your OpenAI dashboard for every API call.

Manage Webhooks and Workspaces

Before launching a massive campaign, your agent runs `verify_api_connection` to confirm the GAN.ai endpoints are breathing. It then checks `get_workspace_info` to ensure you have enough credits for the batch. If you need to route callbacks to your CRM, the agent reads `list_configured_webhooks` to verify the routing exists. It also pulls `list_landing_templates` to ensure the generated video embeds into the right page layout. Your production agent handles the entire deployment check.

Setup guide

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

Create your Agent

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

You initialize MCPServerStreamableHttp with your endpoint URL. Pass it into the mcp_servers array in your Agent constructor. The SDK auto-discovers all 12 tools immediately.

Yes. Your agent calls `get_video_stats` to read open and play rates. You can pipe that data directly into a specialized analytics agent.

The agent invokes `list_landing_templates`. It returns the exact template IDs required for your campaign. Set cacheToolsList=True to speed up the tool discovery phase.

It does. The agent triggers `generate_single_video` for one-off requests. It handles the parameters natively without manual mapping.

The server processes names, emails, and custom text variables injected into the video frames. The MCP protocol runs in an ephemeral V8 Isolate Sandbox. Once the API call resolves, the memory dumps instantly, leaving zero persistent state on Vinkius.

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