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

Q: How do I run complex video searches using Twelve Labs (Video Understanding) and Claude Code?

You execute the search tool with specific criteria. The output is always structured, allowing you to parse it immediately in a shell script or piping it into another command. It's designed for automation.

Q: Is the MCP Server suitable for CI/CD pipelines?

Absolutely. Because this server offers both synchronous (analyzesync) and asynchronous (analyzeasync) tools, you can script multi-stage deployments where one step waits for background processing to finish.

Q: What data type is managed by Twelve Labs (Video Understanding) when using Claude Code?

The core data type handled is indexed assets. The entire lifecycle—from upload to search—is designed around turning raw video files into structured, searchable embeddings.

Q: How can I manage multiple video sources in a script?

You use the collection and index tools. First, createentitycollection sets up the container; then, you systematically run indexasset for every source file path listed in your script.

Q: If I encounter errors during a large video batch job using Twelve Labs (Video Understanding) and Claude Code, where do I look?

You track progress using the multipart tools. Monitoring reportmultipartprogress lets you pinpoint exactly which file or step failed in the sequence, making debugging straightforward.

Automate video intelligence pipelines and run scripts with Twelve Labs (Video Understanding) using Claude Code.

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 Code

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Scripting Video Analysis Jobs

To script a full analysis job, you start by calling `analyze_async`. This tool runs the heavy lifting in the background, allowing your CI/CD pipeline to continue without waiting for segmentation. You can then poll for results later. It's perfect for cron jobs where you need to process hours of video data overnight and just check the status the next morning.

Batch Indexing via CLI

For batch processing, first define your collection using `create_entity_collection`. Then, iterate through a list of assets and run `index_asset` for each one. This pattern is reliable in headless scripts. Claude Code handles the necessary multipart uploads automatically, making it ideal for scripted data ingestion from cloud storage buckets.

Automated Data Retrieval and Reporting

Once videos are indexed, you run a `search` command that accepts parameters like asset IDs or time ranges. This returns machine-readable JSON output. Your script can pipe this output directly into another service—maybe logging the results to a database table or triggering an alert based on what it finds.

Setup guide

Set up Twelve Labs (Video Understanding) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see twelve-labs-video-understanding-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Twelve Labs (Video Understanding) transactions." It will automatically discover and invoke the available Twelve Labs (Video Understanding) tools.

Terminal

claude mcp add --transport http twelve-labs-video-understanding-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "twelve-labs-video-understanding-mcp": {
      "type": "url",
      "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 Code

You execute the `search` tool with specific criteria. The output is always structured, allowing you to parse it immediately in a shell script or piping it into another command. It's designed for automation.

Absolutely. Because this server offers both synchronous (`analyze_sync`) and asynchronous (`analyze_async`) tools, you can script multi-stage deployments where one step waits for background processing to finish.

The core data type handled is `indexed assets`. The entire lifecycle—from upload to search—is designed around turning raw video files into structured, searchable embeddings.

You use the collection and index tools. First, `create_entity_collection` sets up the container; then, you systematically run `index_asset` for every source file path listed in your script.

You track progress using the multipart tools. Monitoring `report_multipart_progress` lets you pinpoint exactly which file or step failed in the sequence, making debugging straightforward.

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