How to Use the Shotstack MCP in OpenAI Agents SDK

Q: How do I track a large batch of videos using Shotstack and OpenAI Agents SDK?

After calling rendervideo, you get a render ID. Use this ID with the getrenderstatus tool to check progress. This lets your agent know exactly when each unique video is ready for deployment.

Q: What if my asset fails? Can I find out what it is?

If a render job uses assets, you can list them by running listassetsfromrender. This pulls up all the specific files tied to that job ID, helping your agent debug why an image or video didn't work.

Q: Does Shotstack support dynamic content changes with OpenAI Agents SDK?

Absolutely. You use createvideotemplate to set up the structure, and then you can feed in different assets via ingestmediasource. This lets your agent generate thousands of personalized ads without changing the underlying video format.

Q: How do I see my history of rendered videos with Shotstack and OpenAI Agents SDK?

You can check recent activity by calling listrecentrenders. It gives you a straightforward list of previous jobs, so your agent doesn't have to rely on memory to find old content.

Build production video pipelines for your OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Shotstack MCP to OpenAI Agents SDK

Create your Vinkius account to connect Shotstack to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Shotstack with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Programmatic Video Rendering with MCP Server

You initiate the entire video process by calling `render_video`, which hands back a render ID. This single action starts generating personalized marketing videos at scale, letting you automate content creation that normally takes hours of manual work. You can check if the job is done—or what went wrong—using `get_render_status`. You'll get constant updates on whether your video rendering pipeline finished successfully or if it needs a retry.

Managing Assets for OpenAI Agents SDK

When you need to upload source media, use `ingest_media_source` to fetch assets into the system. This guarantees that every piece of video content your agent uses is properly sourced and available when rendering begins. Need to know what files are already hosted? Run `list_hosted_assets`. You'll see a list of all media, so you never have to wonder where an asset came from.

Structuring Video Templates for OpenAI Agents SDK

Start by defining your reusable video structure using `create_video_template` to save an edit. This saves the agent from building templates piece by piece every time it runs, keeping everything clean and repeatable. Alternatively, you can check what's available immediately with `list_templates`. It shows all existing structures so the agent knows exactly which video format to use.

Setup guide

Set up Shotstack 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 Shotstack tools at runtime.
3

Create your Agent

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

Run the agent

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

After calling `render_video`, you get a render ID. Use this ID with the `get_render_status` tool to check progress. This lets your agent know exactly when each unique video is ready for deployment.

If a render job uses assets, you can list them by running `list_assets_from_render`. This pulls up all the specific files tied to that job ID, helping your agent debug why an image or video didn't work.

Absolutely. You use `create_video_template` to set up the structure, and then you can feed in different assets via `ingest_media_source`. This lets your agent generate thousands of personalized ads without changing the underlying video format.

You can check recent activity by calling `list_recent_renders`. It gives you a straightforward list of previous jobs, so your agent doesn't have to rely on memory to find old content.

The server primarily deals with media assets and render job IDs. Your agent will be handling uploaded source assets, which are treated as temporary input media sources during processing.

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