Twelve Labs (Video Understanding) MCP Server with 18 Tools for Claude, Cursor, and AI Agents
GDPR Free for SubscribersSearch, analyze, and extract semantic insights from video content using Twelve Labs' powerful multimodal AI models. Vinkius routes your AI agents directly to Twelve Labs (Video Understanding) through a governed connection. 18 tools ready to use with Claude, ChatGPT, Cursor, or any AI agent — no hosting, no setup, connect in 30 seconds.
Ask AI about this server
Compatible with every major AI agent and IDE
Gemini* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
What is the Twelve Labs MCP Server?
The Twelve Labs MCP Server routes AI agents like Claude, ChatGPT, and Cursor directly to Twelve Labs via 18 tools. Search, analyze, and extract semantic insights from video content using Twelve Labs' powerful multimodal AI models. Powered by Vinkius — your credentials stay on your side of the connection, every request is auditable. Connect in under 2 minutes.
Built-in capabilities (18)
Tools for your AI Agents to operate Twelve Labs
Ask your AI agent "List all my Twelve Labs video indexes." and get the answer without opening a single dashboard. With 18 tools connected to real Twelve Labs data, your agents reason over live information, cross-reference it with other MCP servers, and deliver insights you would spend hours assembling manually.
Works with Claude, ChatGPT, Cursor, and any MCP-compatible client. Powered by Vinkius — your credentials never touch the AI model, every request is auditable. Connect in under two minutes.
Why teams choose Vinkius
One subscription gives you the infrastructure to connect your AI agents to thousands of MCP servers — and deploy your own to the Vinkius Edge. Your credentials stay yours. Your data flows directly between your agent and the API. DLP blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade routing and governance, zero maintenance.
Build your own MCP Server with our secure development framework →The Twelve Labs (Video Understanding) App Connector works with every AI agent you already use
…and any MCP-compatible client
Use all 18 Twelve Labs (Video Understanding) tools with your AI agents right now
Vinkius routes your AI agents to Twelve Labs (Video Understanding) through a governed proxy. Beyond a simple connection, you get full visibility into every action your agents perform, with enterprise-grade security and up to 60% savings on AI costs.
Analyze async on Twelve Labs (Video Understanding)
Analyze and segment videos asynchronously
Analyze sync on Twelve Labs (Video Understanding)
Analyze and segment videos synchronously
Confirm multipart upload on Twelve Labs (Video Understanding)
Confirm a multipart upload
Create asset on Twelve Labs (Video Understanding)
Upload content to create an asset
Create entity on Twelve Labs (Video Understanding)
g., a person) within a collection. Create an entity
Create entity collection on Twelve Labs (Video Understanding)
Create an entity collection
Create index on Twelve Labs (Video Understanding)
Create a new index
Create multipart upload on Twelve Labs (Video Understanding)
Create a multipart upload session
Delete index on Twelve Labs (Video Understanding)
Delete an index
Embed async on Twelve Labs (Video Understanding)
Create embeddings asynchronously
Embed sync on Twelve Labs (Video Understanding)
Create embeddings synchronously
Get index on Twelve Labs (Video Understanding)
Retrieve an index by ID
Get indexed asset on Twelve Labs (Video Understanding)
Retrieve an indexed asset
Index asset on Twelve Labs (Video Understanding)
Index an uploaded asset
List indexes on Twelve Labs (Video Understanding)
List all indexes
Report multipart progress on Twelve Labs (Video Understanding)
Report progress for a multipart upload
Search on Twelve Labs (Video Understanding)
Search for moments in videos
Update index on Twelve Labs (Video Understanding)
Update an index name
What the Twelve Labs (Video Understanding) MCP Server unlocks
Connect Twelve Labs to your AI agent to unlock the full potential of video understanding. This server allows your agent to index video files, perform complex semantic searches, and generate deep analytical insights from visual and audio data.
What you can do
- Video Indexing — Create and manage indexes to organize your video library for rapid retrieval and analysis.
- Semantic Search — Query your video content using natural language to find specific moments, objects, or actions without manual tagging.
- Asset Management — Upload videos via URLs or multipart sessions and monitor their indexing status in real-time.
- Deep Analysis — Run synchronous or asynchronous analysis tasks to extract structured data from your video assets.
- Embeddings & Entities — Generate multimodal embeddings and manage entity collections for advanced machine learning workflows.
How it works
1. Subscribe to this server
2. Enter your Twelve Labs API Key
3. Start querying your video data from Claude, Cursor, or any MCP-compatible client
Transform your video archives into searchable, actionable data. Your AI can now 'watch' and understand hours of footage in seconds.
Who is this for?
- Content Creators & Media Teams — quickly find b-roll or specific scenes across massive video libraries.
- Security & Operations — search through hours of footage for specific events or objects using natural language.
- Developers — integrate state-of-the-art video understanding into your AI workflows without building complex pipelines.
Frequently asked questions about the Twelve Labs (Video Understanding) MCP Server
How do I list all my existing video indexes?
You can use the list_indexes tool. It will return a list of all indexes available in your Twelve Labs account, including their IDs and configuration.
Can I search for a specific moment inside my videos using text?
Yes! Use the search tool by providing an index_id and a search query. The AI will find the most relevant timestamps and video segments based on your description.
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 tool with the resulting asset_id and your target index_id to start the processing.
More in this category
Hive AI
10 toolsAutomate content moderation via Hive AI — moderate text, images, video, and detect AI-generated content directly from any AI agent.
Ragas
7 toolsEquip your AI with Ragas to create datasets, run RAG evaluations, and track experiment metrics directly from your workflow.
HrFlow.ai
10 toolsAI-powered talent acquisition API for parsing, matching, and reasoning.
Jina AI (Search Foundation & LLM Grounding)
6 toolsPower your RAG and search via Jina AI — generate embeddings, rerank documents, read URLs, and perform semantic web search.
You might also like
Clearstory
8 toolsManage construction change orders and T&M tags via Clearstory — track projects, monitor CORs, and manage project rates directly from any AI agent.
Steam
7 toolsAccess game data, player profiles, and community content from the world largest PC gaming platform and digital storefront.
Doodle
10 toolsManage group scheduling via Doodle — create meeting polls, track participant votes, handle comments, and close polls directly from any AI agent.
SemVer Version Manager
2 toolsStop LLMs from guessing software versions. Deterministically evaluate semantic version bounds, compatibilities, and sort releases perfectly.
We built the connector to Twelve Labs (Video Understanding). Now put your agents to work. Fully governed.
Vinkius is the AI Gateway with managed hosting. Stop building connectors. Every connection runs inside eight layers of security.
Hosted, sandboxed, and live on AWS. You don't provision anything. You don't maintain anything. You connect.
Every tool call, every token, every response. Logged and auditable. Data flows direct from Twelve Labs (Video Understanding) to your agent. Nothing is stored on our side. Ever.
Eight governance layers on every request. Sensitive data redacted before it reaches the model. Kill switch if anything goes sideways. Always on.