How to Use the Twelve Labs (Video Understanding) MCP in OpenAI Agents SDK

Q: Can Twelve Labs (Video Understanding) process data in batches for OpenAI Agents SDK?

Absolutely. You can queue up large jobs using analyzeasync to process multiple videos concurrently. The agent tracks progress via tools like reportmultipartprogress, ensuring you know when the entire batch is ready.

Extract structured insights from video content with 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 Twelve Labs (Video Understanding) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Twelve Labs (Video Understanding) 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 Twelve Labs (Video Understanding) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Segmenting large videos asynchronously

Need to process hours of footage without stalling the agent? Use `analyze_async` to break down entire videos into smaller, manageable segments. This runs in the background, so your agent can keep working on other tasks while the heavy lifting happens. Once the segmenting is complete, you'll have actionable metadata that lets your agent proceed with deep analysis or targeted searches using tools like `search`.

Building structured video knowledge bases

The agent handles asset creation and indexing in one flow. First, it calls `create_asset` to upload content, then uses `index_asset`. This process builds a searchable backbone for your videos. After indexing, the system can build specific profiles of people or objects using `create_entity`, making sure every key person mentioned is tracked and linked across multiple video sources.

Retrieving pinpoint details from assets

Don't sift through transcripts. To find a specific moment, the agent uses `search` to look for semantic matches within your content corpus. This function targets moments in videos based on keywords or themes. If you need to pull down metadata about that search result, you can use `get_indexed_asset`. It fetches the exact data structure associated with a specific piece of video content.

Setup guide

Set up Twelve Labs (Video Understanding) 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 Twelve Labs (Video Understanding) tools at runtime.
3

Create your Agent

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

Run the agent

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

The MCP Server gives your agents structured tools to analyze complex media. Instead of just sending text, the agent can now call `analyze_sync` or `search`. This moves your deployment beyond simple Q&A and into deep content extraction.

This server primarily handles video assets, which are stored as multipart uploads. The agent interacts with the resulting metadata, such as indices and entity collections, but the core source material is video content.

Absolutely. You can queue up large jobs using `analyze_async` to process multiple videos concurrently. The agent tracks progress via tools like `report_multipart_progress`, ensuring you know when the entire batch is ready.

Yes, it enforces structure by allowing the agent to create and manage specific `create_entity` collections. This keeps all related information—like a person's name or car model—grouped together in a verifiable way.

The server analyzes video content to extract semantic insights. This includes creating searchable indices, segmenting videos by time, and building profiles of entities found within the footage.

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