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

Q: How do I find specific details in a video using Twelve Labs (Video Understanding) and Windsurf?

You start by running indexasset to ingest the video into an index. Once indexed, you call the search tool with descriptive language. The result gives you time codes pointing exactly where those semantic insights occur.

Q: How does Twelve Labs (Video Understanding) help with data privacy when using Windsurf?

The server touches indexed assets data. Because this information is managed within the MCP Server's isolated sandbox, your agent only interacts with the necessary tokens and results, keeping the source data contained.

Q: What tools are available for managing video metadata?

You have several options: listindexes shows you what indexes exist, while createindex lets you build a new one. You can also use updateindex if you need to rename something.

Get deep semantic insights from video content, automatically chained for Windsurf.

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 Windsurf

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Video Content

The `analyze_async` tool processes and segments videos in the background. You set a goal—like finding all instances of 'blue car'—and Cascade handles the lengthy upload, analysis, and segmentation process autonomously. It executes this multi-step plan entirely within Windsurf without needing you to prompt for each phase. Just tell it what you want to find, and your agent figures out the rest.

Build Searchable Knowledge Bases

To make video content searchable, first use `create_entity` or `create_entity_collection`. These tools establish the structure for what you want to find—like a list of people or specific objects. You define the container, and then your agent proceeds with indexing. After setting up the collection, running `index_asset` sends the video data into the system. This builds an index that lets Windsurf search not just keywords, but actual moments in time.

Retrieve Specific Insights

Once your content is indexed, you use the `search` tool to pull out specific moments or data points. You send a query—say, 'show me when the speaker mentions Q3 earnings'—and it returns exact timestamps. The agent then uses this information with tools like `get_indexed_asset` so that the final result is actionable context, not just raw search results.

Setup guide

Set up Twelve Labs (Video Understanding) MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Twelve Labs (Video Understanding) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Twelve Labs (Video Understanding) payment history." If connected, Cascade will call the Twelve Labs (Video Understanding) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

You start by running `index_asset` to ingest the video into an index. Once indexed, you call the `search` tool with descriptive language. The result gives you time codes pointing exactly where those semantic insights occur.

Yep. For big uploads, it handles the complexity of multipart sessions using tools like `create_multipart_upload` and `report_multipart_progress`. This means you can set your goal even if the source file is massive.

The server touches `indexed assets` data. Because this information is managed within the MCP Server's isolated sandbox, your agent only interacts with the necessary tokens and results, keeping the source data contained.

You have several options: `list_indexes` shows you what indexes exist, while `create_index` lets you build a new one. You can also use `update_index` if you need to rename something.

You get highly specific, semantic results tied directly to the video timeline. Instead of just 'yes' or 'no,' you get time-stamped coordinates showing exactly where the AI detected the requested moment.

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