An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Twelve Labs Video Understanding to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Let your agent watch and search through video archives.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 18 capabilities

We ship only the actions that matter.

Capability set01 / 05

01-04

4 capabilities in this set.

Part of 18 available through Twelve Labs.

  1. 01

    Embed async

    This capability creates multimodal embeddings in the background so your agent can continue other tasks.

  2. 02

    Update index

    Use this to change the name of an existing index.

  3. 03

    Analyze sync

    This capability performs immediate video segmentation and analysis.

  4. 04

    Confirm multipart upload

    Use this to finalize a multipart upload session.

Capability set02 / 05

05-08

4 capabilities in this set.

Part of 18 available through Twelve Labs.

  1. 05

    Create asset

    This capability uploads content to generate a new video asset.

  2. 06

    Create entity collection

    Use this to set up a new collection for managing specific entities.

  3. 07

    Create entity

    This capability adds a specific entity, like a person, to an existing collection.

  4. 08

    Create index

    Use this to initialize a new video index.

Capability set03 / 05

09-12

4 capabilities in this set.

Part of 18 available through Twelve Labs.

  1. 09

    Create multipart upload

    This capability starts a new multipart upload session for large files.

  2. 10

    Delete index

    Use this to remove an index from your library.

  3. 11

    Embed sync

    This capability generates embeddings immediately for real-time needs.

  4. 12

    Get index

    Use this to pull details for a specific index using its ID.

Capability set04 / 05

13-15

3 capabilities in this set.

Part of 18 available through Twelve Labs.

  1. 13

    Get indexed asset

    This capability retrieves information about a specific indexed asset.

  2. 14

    List indexes

    Use this to see all the indexes currently in your account.

  3. 15

    Report multipart progress

    This capability tracks the status of an ongoing multipart upload.

Capability set05 / 05

16-18

3 capabilities in this set.

Part of 18 available through Twelve Labs.

  1. 16

    Search

    Use this to find specific moments or actions within your video content using natural language.

  2. 17

    Index asset

    This capability triggers the indexing process for an uploaded asset.

  3. 18

    Analyze async

    This capability runs video segmentation and analysis tasks in the background.

Real work

What teams actually run

01

Media Asset Retrieval

A video editor asks their agent to find every clip containing a sunset to build a montage.

02

Security Event Detection

An operations team searches through surveillance footage for a specific vehicle type using natural language.

03

Automated Video Tagging

A developer uses the indexing capabilities to automatically organize a massive archive of raw footage.

04

Content Analysis

A researcher runs asynchronous analysis to extract structured data from a series of recorded lectures.

Automate a task

Put Twelve Labs to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Twelve Labs works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Twelve Labs to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1024ms average. Fast in production.

Twelve Labs is checked daily against the live service.

Daily averagePeak 1215ms
Oct 3Today
Fastest day
815ms
Slowest day
1215ms
14-day trend
Improving-8%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 18 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Twelve Labs, so you can see the experience inside your AI.

It does not authenticate your account with Twelve Labs. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Twelve Labs Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_Vgl5VVTXIogBXlRhR1Xxpl2YsHWFIR0xQ7beKVtS/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Twelve Labs capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "twelve-labs-video-understanding-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_Vgl5VVTXIogBXlRhR1Xxpl2YsHWFIR0xQ7beKVtS/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Twelve Labs in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Twelve Labs owners hand off.

This MCP is built for anyone managing large volumes of video data who needs to extract information without manual scrubbing.

  • 01

    Content Creators

    They hand off the task of finding specific b-roll or scenes to their agent.

  • 02

    Security Operators

    They use the agent to search through hours of footage for specific events or objects.

  • 03

    Developers

    They use the capabilities to add video understanding to their own AI workflows.

FAQ

Questions Twelve Labs owners ask.

  • 01

    How do I use this MCP with my AI client?

    You connect once through the Vinkius platform. After you provide your Twelve Labs API key, your agent in Claude, Cursor, or Windsurf will have direct access to the capabilities.

  • 02

    Can I search for things in video using plain English?

    Yes. The semantic search capability allows you to query your video content using natural language to find specific moments, objects, or actions.

  • 03

    Does this MCP handle large video files?

    Yes. It includes capabilities for multipart uploads and can manage large assets through dedicated upload sessions.

  • 04

    What is the difference between sync and async analysis?

    Synchronous analysis provides results immediately, while asynchronous analysis runs the task in the background so your agent can perform other tasks simultaneously.

  • 05

    Do I need to tag my videos before searching?

    No. The indexing and semantic search capabilities allow the agent to understand the content without any manual tagging.

  • 06

    How do I list all my existing video indexes?

    You can use the list_indexes capability. It will return a list of all indexes available in your Twelve Labs account, including their IDs and configuration.

  • 07

    Can I search for a specific moment inside my videos using text?

    Yes! Use the search capability by providing an index_id and a search query. The AI will find the most relevant timestamps and video segments based on your description.

  • 08

    How do I add a new video to an index for analysis?

    First, use create_asset with a public URL to upload the video. Then, use the index_asset capability with the resulting asset_id and your target index_id to start the processing.

Explore

More in AI Frontier

Suggestions

Connect Twelve Labs to Claude, Cursor, ChatGPT & more