How to Use the Dopplio MCP in OpenAI Agents SDK

Q: How do I connect the Dopplio MCP Server to my OpenAI Agents SDK project?

Install the package with pip install openai-agents. Initialize the connection to the MCP Server using MCPServerStreamableHttp(params=MCPServerStreamableHttpParams(url="YOURVINKIUSURL")) in an async with block, then pass the server instance inside the mcpservers list when initializing your Agent.

Q: How does OpenAI Agents SDK handle long-running video renders in Dopplio?

Your agent calls generatevideo to start the job, then periodically executes getrenderstatus to monitor progress. The SDK handles these checks natively within your agent loop, allowing the agent to transition to other tasks or pause until the status returns as completed.

Run automated video personalization workflows safely with OpenAI Agents SDK and guardrails that watch every render.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dopplio MCP to OpenAI Agents SDK

Create your Vinkius account to connect Dopplio 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 Dopplio with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe video generation with OpenAI Agents SDK

The `generate_video` tool lets your agent initiate personalized video generation by sending template and personalization variables to the API. Your OpenAI agent handles the parameters, while the SDK's built-in guardrails validate the payload before hitting the server. This setup prevents broken templates from wasting your rendering credits. You get direct trace visibility in your OpenAI dashboard to debug payload schemas instantly when an agent tries to customize a clip.

Track rendering status across agent handoffs

The `get_render_status` tool checks the progress of an active render job to keep your multi-agent system synchronized. When a specialized video-generation agent finishes initiating a job, it hands off the task to a monitoring agent that polls this endpoint. Your monitoring agent uses `get_video_details` to grab the final MP4 URL once the render completes. Because the OpenAI Agents SDK manages these agent handoffs natively, you don't have to write custom state machine code to handle the wait times.

Capture web context to personalize PDFs and videos

The `capture_screenshot` tool takes a URL and returns a visual snapshot of a target website to use in your outreach templates. Your agent uses this raw visual data to build context before invoking `render_pdf` with custom HTML or web links. To keep performance high, configure `cacheToolsList=True` in your MCP Server setup. This stops the agent from querying the server for tool definitions on every single page capture, saving precious round-trip latency.

Setup guide

Set up Dopplio 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 Dopplio tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Dopplio tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Dopplio 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="Dopplio Agent",
            instructions="You have access to Dopplio 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 Dopplio. 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 Dopplio 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 Dopplio MCP in OpenAI Agents SDK

Install the package with `pip install openai-agents`. Initialize the connection to the MCP Server using `MCPServerStreamableHttp(params=MCPServerStreamableHttpParams(url="YOUR_VINKIUS_URL"))` in an `async with` block, then pass the server instance inside the `mcp_servers` list when initializing your Agent.

Your agent calls `generate_video` to start the job, then periodically executes `get_render_status` to monitor progress. The SDK handles these checks natively within your agent loop, allowing the agent to transition to other tasks or pause until the status returns as completed.

Yes, you configure this at the agent definition level in your Python code. You can limit your agent to only see `list_videos` and `get_video_details` if you want a read-only agent, protecting your credit balance from accidental generation loops.

Use the OpenAI developer dashboard to trace the exact HTML payload sent to `render_pdf`. The dashboard shows the raw tool arguments and server responses, letting you pinpoint syntax errors in your generated HTML immediately.

All rendering occurs inside the Vinkius MCP sandbox, meaning your target URLs, HTML strings, and generated video files are processed securely. Your credentials never touch the open web or persistent agent memory.

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