For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Sample appsIntegrationsDiscordPlaygroundDevEx repo
GuidesSDK ReferenceAPI Reference
GuidesSDK ReferenceAPI Reference
  • Get Started
    • Introduction
    • Quickstart
    • Manage your plan
    • Rate limits
    • Release notes
    • Migration guide
  • Guides
    • Search
    • Analyze videos
    • Segment videos
    • Create embeddings
  • Concepts
    • Models
    • Upload and processing methods
    • Indexes
    • Modalities
    • Multimodal large language models
  • Cloud partner integrations
    • Amazon Bedrock
  • Advanced
    • Organizations
    • Fine-tuning
    • Webhooks
    • Metadata
    • Model context protocol
    • Claude Code Plugin
  • Resources
    • Platform overview
    • Playground
    • TwelveLabs SDKs
    • Frequently asked questions
    • Use cases
    • Sample applications
    • Partner integrations
    • From the community
LogoLogo
Sample appsIntegrationsDiscordPlaygroundDevEx repo
On this page
  • Prerequisites
  • Set up the plugin
  • Use the plugin
  • Troubleshooting
  • Next steps
Advanced

Claude Code Plugin

Was this page helpful?
Previous

Platform overview

Next
Built with

Use the TwelveLabs Claude Code plugin to search videos, analyze their content, and create embeddings without leaving Claude Code.

Note

The Claude Code plugin and the MCP server both connect Claude to the TwelveLabs Video Understanding Platform. Use the plugin if you work exclusively in Claude Code. Use the MCP server if you work across multiple AI clients.

Key features:

  • Video search: Find specific moments in your videos using natural language, images, or combined text and image queries.
  • Video analysis: Generate summaries, extract insights, create action items, and ask questions about your video content.
  • Embeddings: Create multimodal embeddings for similarity search, clustering, recommendation systems, or other downstream AI tasks.
  • Natural language or slash commands: Describe tasks in plain English or run commands directly using the /twelvelabs: namespace.
  • Google Drive support: Index videos directly from Google Drive file or folder links.

Prerequisites

  • To use the platform, you need an API key:

    1

    If you don’t have an account, sign up for a free account.

    2

    Go to the API Keys page.

    3

    If you need to create a new key, select the Create API Key button. Enter a name and set the expiration period. The default is 12 months.

    4

    Select the Copy icon next to your key to copy it to your clipboard.

  • Claude Code installed on your machine.

Set up the plugin

1

Set your TwelveLabs API key as an environment variable.

$export TWELVELABS_API_KEY=<YOUR_API_KEY>
2

In Claude Code, add the TwelveLabs plugin marketplace.

/plugin marketplace add twelvelabs-io/twelve-labs-claude-code-plugin
3

Install the plugin.

/plugin install twelvelabs@twelvelabs-plugins
4

Restart Claude Code.

Use the plugin

The plugin adds slash commands to Claude Code under the /twelvelabs: namespace. You can also describe tasks in plain English, and Claude will invoke the appropriate commands. See the Natural language usage section in the GitHub repository for examples.

Before searching or analyzing, index your videos using /twelvelabs:index-video.

For the full list of commands and usage examples, see the TwelveLabs Claude Code plugin repository on GitHub.

Examples:

  • /twelvelabs:search: Find specific moments using a natural language query.
  • /twelvelabs:analyze: Analyze a video to generate text based on its content.
  • /twelvelabs:embed: Create embeddings for downstream AI tasks.

Troubleshooting

If you encounter issues after installation, see the Troubleshooting section in the GitHub repository.

Next steps

  • Read the TwelveLabs Claude Code plugin blog post for an overview of the plugin and its use cases.
  • See the full command reference on GitHub.