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

Q: How do I search for moments in videos using Twelve Labs (Video Understanding) and Claude Desktop?

You call the search tool. It takes your query and searches across all indexed video assets. The MCP Server returns precise time codes and segments where that content appears.

Q: What is the difference between synchronous and asynchronous analysis using Twelve Labs (Video Understanding) and Claude Desktop?

Synchronous calls (analyzesync) process small jobs immediately, blocking your agent until done. Asynchronous tools (analyzeasync) send big jobs to a background queue, letting you keep working while progress reports come back later.

Q: Does the MCP Server support handling large video files for Twelve Labs (Video Understanding) and Claude Desktop?

Absolutely. Use createmultipartupload to break up massive videos into manageable parts. The system tracks progress using reportmultipartprogress until the entire file is uploaded.

Q: Can I use Twelve Labs (Video Understanding) and Claude Desktop to identify specific people?

Yes, you can use createentity to define an entity—like a person—within your video collection. This lets you search for that specific individual across different videos.

Analyze video content and extract deep insights right from your local machine using Claude Desktop.

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 Claude Desktop

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Managing Video Indexes with Claude Desktop

Set up a new knowledge base for your videos. Use `create_multipart_upload` to handle large files, followed by `index_asset`. This process builds the necessary structure using tools like `list_indexes` and allows you to retrieve index details via `get_index`. You're in charge of the whole data lifecycle. If an index is outdated or wrong, you can delete it with `delete_index`, or update its name using `update_index`. This keeps your local data clean.

Generating Semantic Embeddings for Claude Desktop

Need to convert video moments into searchable data points? Run `embed_async` or `embed_sync`. These tools take the indexed material and generate vector embeddings, making specific segments retrievable later on. The results are critical for semantic search. Embeddings allow your agent to understand what a user *means*, not just what they typed. You'll get highly accurate context when querying video data.

Search Video Content with the MCP Server for Claude Desktop

Find specific moments that match a query using `search`. This is how you pinpoint key actions or conversations in hours of footage. The system supports running full analyses via `analyze_async` to process huge datasets without freezing your machine. Beyond searching, the MCP Server helps define context by allowing you to run `create_entity` on people or objects within a video collection, giving structure to unstructured media.

Setup guide

Set up Twelve Labs (Video Understanding) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Twelve Labs (Video Understanding) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Twelve Labs (Video Understanding) MCP configuration

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

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under twelve-labs-video-understanding-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 Claude Desktop

You call the `search` tool. It takes your query and searches across all indexed video assets. The MCP Server returns precise time codes and segments where that content appears.

Synchronous calls (`analyze_sync`) process small jobs immediately, blocking your agent until done. Asynchronous tools (`analyze_async`) send big jobs to a background queue, letting you keep working while progress reports come back later.

Absolutely. Use `create_multipart_upload` to break up massive videos into manageable parts. The system tracks progress using `report_multipart_progress` until the entire file is uploaded.

Yes, you can use `create_entity` to define an entity—like a person—within your video collection. This lets you search for that specific individual across different videos.

The server touches raw video content, metadata (time codes), and generated vector embeddings. Always ensure your local database handles the security requirements for all these data types.

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