How to Use the Twelve Labs (Video Understanding) MCP in Vercel AI SDK

Q: How do I search video content using Twelve Labs (Video Understanding) and Vercel AI SDK?

You simply call the search tool from your agent. The MCP Server sends back a list of time-stamped results, allowing you to display that data stream right in your React frontend as it appears.

Q: Can I manage video assets with Twelve Labs (Video Understanding) and Vercel AI SDK?

Yes. You use createmultipartupload to handle large files reliably. Once the upload is confirmed, you can call indexasset to prepare that content for querying via your MCP Server.

See video insights stream live in the UI using Vercel AI 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 Vercel AI SDK

Create your Vinkius account to connect Twelve Labs (Video Understanding) to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search for specific moments

The `search` tool lets your agent query a video's content directly. Instead of just finding keywords, it locates specific time segments that match semantic concepts. When a user asks, 'Show me when the CEO mentioned Q3 targets,' the MCP Server returns precise timestamps and context from the raw video data.

Embed and index assets

You need to make the videos searchable first. Use `embed_sync` or `embed_async` to convert the video into high-dimensional embeddings. These vectors capture the meaning of the content, not just the words. The resulting data lets you call `index_asset`, storing that knowledge in an index accessible by other tools. This means your client can treat video footage like a traditional database.

Track specific entities

The `create_entity` tool helps you pull out structured information from the video, such as identifying people or objects and grouping them into collections. Your agent can run this to build a registry of every person mentioned in the footage. This is far better than just transcribing names; it provides contextual data points for follow-up queries.

Setup guide

Set up Twelve Labs (Video Understanding) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Twelve Labs (Video Understanding) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Twelve Labs (Video Understanding) transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You simply call the `search` tool from your agent. The MCP Server sends back a list of time-stamped results, allowing you to display that data stream right in your React frontend as it appears.

Yes. You use `create_multipart_upload` to handle large files reliably. Once the upload is confirmed, you can call `index_asset` to prepare that content for querying via your MCP Server.

This server touches raw video content, generated embeddings, indexed assets, and structured entity records. Your agent handles this entire lifecycle through the streaming API.

Nope. Since you're building a user-facing product, your agent manages the calls to our MCP Server, letting you focus on the real-time UI experience.

The server processes video content, embeddings, indices, and entities. We handle the authentication via an endpoint token provided by your agent client.

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