How to Use the Twelve Labs (Video Understanding) MCP in Google ADK

Q: Can Twelve Labs (Video Understanding) handle large-scale indexing for Google ADK?

Yes. The indexasset tool is designed for this. Agents can manage multiple uploads using createmultipartupload, ensuring that massive, multi-part files are indexed completely and reliably.

Build enterprise video intelligence workflows with Google ADK.

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 Google ADK

Create your Vinkius account to connect Twelve Labs (Video Understanding) to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Batch processing of large media files

For massive datasets, the agent uses `analyze_async` to process videos in the background. This scales efficiently across Google Cloud infrastructure, handling segmenting for countless hours of footage. The system then generates detailed metadata that your Gemini-powered agents can consume directly, making it ideal for feeding data into BigQuery or Vertex AI.

Creating and managing video indexes

Agents establish a structured knowledge base using `create_index` and manage the lifecycle with tools like `delete_index`. This process ensures your videos are cataloged for long-context reasoning. The agent can then use `get_index` to verify that the metadata structure is correct before running complex queries against the video content.

Deep object and person tracking

The agent identifies key subjects and relationships within your videos using `create_entity`. It doesn't just list names; it builds comprehensive collections of people, objects, or concepts. This structured data allows the LlmAgent to maintain context over millions of tokens, relating a person seen in Video A to an object mentioned in Video Z.

Setup guide

Set up Twelve Labs (Video Understanding) MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Twelve Labs (Video Understanding) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Twelve Labs (Video Understanding)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Twelve Labs (Video Understanding) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

The MCP Server allows your agents to treat video content like structured, queryable data. Instead of just summarizing a clip, the agent can pinpoint specific moments using `search` and then pass that detailed metadata into BigQuery.

The primary data type is video content itself, which must first be uploaded to create an asset. The agents then work with the resulting structured metadata and indexes that point back to specific time segments of the original video.

Yes. The `index_asset` tool is designed for this. Agents can manage multiple uploads using `create_multipart_upload`, ensuring that massive, multi-part files are indexed completely and reliably.

It spans multimodal analysis: from initial content ingestion (`create_asset`) to deep semantic search (`search`), all while maintaining an enterprise-grade connection to cloud data warehousing like BigQuery.

It builds integrity by enforcing categorization. When you use `create_entity`, the system groups related information under a specific collection, which prevents data silos and keeps all derived knowledge centralized.

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