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

Q: How does LlamaIndex use Twelve Labs (Video Understanding) to improve search?

It takes the raw output from tools like search and converts those results into embeddings. This allows you to query not just keywords, but the actual meaning of what happened in the video.

Q: Can I query past session data using LlamaIndex and the Twelve Labs (Video Understanding) MCP Server?

Yes. By saving indexed results via createindex and retrieving them later, you can build a history of video insights that's grounded in actual API calls, not guesses.

Q: If I need to clean up old data, which tool does LlamaIndex use with the Twelve Labs (Video Understanding) MCP Server?

You can use deleteindex to remove entire sets of insights you no longer want. It's a clean way to manage your vector store.

Build RAG pipelines for video knowledge with LlamaIndex.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic Video Search using LlamaIndex and MCP Server

The `search` tool finds specific moments in videos, but the real power is what happens next. You use `embed_sync` or `embed_async` to turn those search results into embeddings. This lets you store them in a vector store. When a user asks a follow-up question later, LlamaIndex queries the vector store for grounded answers based on past video data.

Creating Structured Knowledge Graphs with LlamaIndex

You build your knowledge base by first calling `create_entity_collection`, defining what kind of things you're tracking. Then, using `create_entity`, you feed it the specific details—like 'a person named Joe.' LlamaIndex then combines this structured data with unstructured video insights, creating a complete picture for RAG applications.

Managing Video Assets and Indices via LlamaIndex

When you upload content using `create_asset`, the MCP Server gives you an ID. You then use `index_asset` to process that asset and store its key information in a retrievable index. This systematic approach ensures that every piece of video data is properly cataloged, making it ready for retrieval at any time.

Setup guide

Set up Twelve Labs (Video Understanding) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Twelve Labs (Video Understanding) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Twelve Labs (Video Understanding) tools.",
)
response = await agent.run("List recent Twelve Labs (Video Understanding) data")

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 LlamaIndex

It takes the raw output from tools like `search` and converts those results into embeddings. This allows you to query not just keywords, but the actual meaning of what happened in the video.

You're primarily dealing with multimodal insights: video content hashes, structured metadata about people and assets, and text-based search results that form the basis of your knowledge base.

Yes. By saving indexed results via `create_index` and retrieving them later, you can build a history of video insights that's grounded in actual API calls, not guesses.

You can use `delete_index` to remove entire sets of insights you no longer want. It's a clean way to manage your vector store.

The server touches both raw video content and associated metadata, which are then converted into embeddings and stored within a queryable index.

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