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

Q: How do I search for video segments with Twelve Labs (Video Understanding) and Cursor?

You use the search tool. The agent will prompt you for your query, and it returns precise time codes and relevant data points that you can immediately inject into your code.

Q: When should I prefer embedasync over embedsync using Twelve Labs (Video Understanding) and Cursor?

If the embedding job is large, use embedasync. It queues the work and lets your coding session continue while the vectors are generated. Use sync only for small, immediate tasks.

Q: Can I manage my video data structure using the MCP Server in Cursor?

Yes. You can createentitycollection to organize related videos and use tools like getindex to retrieve metadata about specific indexes within your project.

Q: Does Twelve Labs (Video Understanding) support updating existing video data?

Yes. You can run updateindex if the name or scope of an index changes, maintaining data integrity across your code base. This keeps your projects reliable.

Inject live video insights into your code using Twelve Labs (Video Understanding) with Cursor.

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 Cursor

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Setting up Video Indexing in Cursor

When writing code, you can start by creating an index of your videos. Use `create_multipart_upload` to upload the raw data chunk by chunk. Then, run `index_asset` to make the video content available for context within your current coding session. The agent mode in Cursor handles the workflow. It calls tools like `list_indexes` and `get_index` so you can verify that the assets are properly indexed before writing any retrieval logic.

Generating Embeddings for Code Context with Cursor

Your code needs more than just text; it needs understanding. Use `embed_async` or `embed_sync` to generate vector embeddings from your video data. This process turns visual concepts into numerical vectors that Python or JavaScript can easily query. The AI generates working code that uses these live API responses directly, meaning you're not using mock stubs; the context comes straight from the MCP Server.

Searching Video Content with the MCP Server in Cursor

Need to know what happened at a specific point in time? The `search` tool lets your agent query video segments based on semantic meaning. You can even use `create_entity` to filter results, say, only for actions involving 'person A'. The system also supports running full analysis using `analyze_async`. This gives you the detailed output needed to complete a function or write a complex data transformation.

Setup guide

Set up Twelve Labs (Video Understanding) MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Twelve Labs (Video Understanding) MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Twelve Labs (Video Understanding) transactions." If the MCP tools are loaded correctly, Cursor will call the Twelve Labs (Video Understanding) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "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 Cursor

You use the `search` tool. The agent will prompt you for your query, and it returns precise time codes and relevant data points that you can immediately inject into your code.

If the embedding job is large, use `embed_async`. It queues the work and lets your coding session continue while the vectors are generated. Use sync only for small, immediate tasks.

Yes. You can `create_entity_collection` to organize related videos and use tools like `get_index` to retrieve metadata about specific indexes within your project.

Yes. You can run `update_index` if the name or scope of an index changes, maintaining data integrity across your code base. This keeps your projects reliable.

This server touches video content, metadata, and generated vector embeddings. When working in Cursor's agent mode, you must ensure the code handles all these types securely.

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