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

Q: How do I build a dashboard showing video insights using Twelve Labs (Video Understanding) and Cline?

First, use createentity to define the data points you need. Then, write a script that uses indexasset to process videos into an index. Finally, call the search tool from your code and output the results into a component file.

Q: Can Cline handle large-scale video uploads?

Yes. It manages complex transfers using createmultipartupload. You can monitor progress with reportmultipartprogress, ensuring that massive batches of videos get into the system correctly.

Q: What data types does Twelve Labs (Video Understanding) interact with when running in Cline?

The primary data type touched by this MCP Server is indexed assets. The entire purpose of the workflow is to take raw video content and transform it into retrievable, structured vector embeddings.

Q: What if I need to update an existing index?

You can use the updateindex tool. This lets you change the name or metadata of a previously created index without having to delete and rebuild the entire collection, which saves time.

Q: What is the difference between using analyzesync vs analyzeasync with Twelve Labs (Video Understanding) and Cline?

Analyzesync runs the analysis in memory immediately; it's fast for small tests. However, if you are running a full pipeline script, analyzeasync is better because it manages background processing without blocking your code execution.

Build data pipelines and code components with Twelve Labs (Video Understanding) using Cline.

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 Cline

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Searchable Video Indexes

To start, you'll use the `create_entity_collection` tool to define your desired data structure. This is like writing the schema for what you want the AI to track—whether it’s people or products. You run this step first. The next logical step is using `create_index`. These tools work together to build a foundational knowledge base that other code components can rely on.

Process and Embed Video Data

You feed the raw video data into the system, initiating an upload session via `create_multipart_upload`. Once uploaded, you run embeddings using either `embed_sync` or `embed_async`. These tools convert complex visual moments into numerical vectors that machines can actually compare. Cline executes these functions sequentially: Upload -> Embeddings -> Indexing. It's a full data ingestion pipeline in one go.

Query Video Moments Programmatically

After everything is indexed, you use the `search` tool to run queries directly from your script. You pass parameters—like specific time ranges or concepts—and it returns structured data. Cline can then take this output and feed it into another component, like generating a JSON file or populating a database record automatically.

Setup guide

Set up Twelve Labs (Video Understanding) MCP in Cline

Prerequisites

VS Code with Cline extension installed
Active Vinkius subscription with a valid endpoint token

1

Open Cline MCP settings

Click the Cline icon in the VS Code sidebar to open the Cline panel. Then click the MCP Servers icon (server stack) at the top-right corner of the panel.
2

Add a remote server

Click "Remote Servers" at the top, then click "Add Remote MCP". In the Name field, type twelve-labs-video-understanding-mcp. In the URL field, paste your Vinkius endpoint: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp. Get your token from cloud.vinkius.com.
3

Enable the server

After saving, the server appears in the Cline MCP panel. Toggle the switch to enable it. The status indicator turns green when the connection is live.
4

Start using tools

Return to the Cline chat and ask: "Check my latest Twelve Labs (Video Understanding) refund status." Cline will discover the available tools and request your approval before invoking each one — giving you full control over every action.

Cline MCP Settings

{
  "mcpServers": {
    "twelve-labs-video-understanding-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cline

First, use `create_entity` to define the data points you need. Then, write a script that uses `index_asset` to process videos into an index. Finally, call the `search` tool from your code and output the results into a component file.

Yes. It manages complex transfers using `create_multipart_upload`. You can monitor progress with `report_multipart_progress`, ensuring that massive batches of videos get into the system correctly.

The primary data type touched by this MCP Server is `indexed assets`. The entire purpose of the workflow is to take raw video content and transform it into retrievable, structured vector embeddings.

You can use the `update_index` tool. This lets you change the name or metadata of a previously created index without having to delete and rebuild the entire collection, which saves time.

`Analyze_sync` runs the analysis in memory immediately; it's fast for small tests. However, if you are running a full pipeline script, `analyze_async` is better because it manages background processing without blocking your code execution.

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