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

Q: How does Twelve Labs (Video Understanding) help LangChain analyze long videos?

You use analyzeasync to process huge videos in the background. Instead of waiting, your agent gets a job ID and can continue building other parts of the workflow while the analysis runs.

Q: Can I query past results using LangChain and the Twelve Labs (Video Understanding) MCP Server?

Absolutely. By creating indexes first using createindex, your agent can later retrieve specific asset information or search results from those stored indexes.

Q: If I need to delete video data, which tool does LangChain use with the Twelve Labs (Video Understanding) MCP Server?

You'll use deleteindex if you want to wipe out a whole collection of indexed insights. You can also call updateindex to rename it first.

Build complex video analysis chains with LangChain.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Executing Multi-Step Video Search with MCP Server

The `search` tool lets you find specific moments and insights deep inside video content. You can feed the results of one step—say, a list of candidate timestamps—directly into another tool for further analysis. You'll build full reasoning pipelines where your agent decides exactly which action to take next: whether it needs to `analyze_sync` the segment or just run a quick metadata check.

Structuring Video Knowledge Bases using LangChain

Start by defining your data structure with `create_entity_collection`. This sets up the container for all the video insights, like grouping 'Person A' or 'Product B.' After that, you use `create_entity` to populate it with specific details found in the video. This allows your agent chain to manage complex relationships between assets and entities automatically. You never have to manually worry about schema versioning.

Managing Large Video Uploads via LangChain

For big videos, you can't just upload them once; you need multipart handling. The `create_multipart_upload` tool starts the session, and then your agent uses `report_multipart_progress` to track how far along the file transfer is. This robust flow ensures that even massive video files get processed correctly by the MCP Server, keeping your workflow stable from start to finish.

Setup guide

Set up Twelve Labs (Video Understanding) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Twelve Labs (Video Understanding) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "twelve-labs-video-understanding-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Twelve Labs (Video Understanding) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You use `analyze_async` to process huge videos in the background. Instead of waiting, your agent gets a job ID and can continue building other parts of the workflow while the analysis runs.

The server handles video files for initial processing. Once indexed, you'll be working with structured metadata about people and assets, which is stored as entities.

Absolutely. By creating indexes first using `create_index`, your agent can later retrieve specific asset information or search results from those stored indexes.

You'll use `delete_index` if you want to wipe out a whole collection of indexed insights. You can also call `update_index` to rename it first.

The server touches asset metadata and video content hashes, which are stored as indexes. This allows your agent to track exactly what piece of media generated that insight.

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