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

Q: How do I build a full analysis workflow using Twelve Labs (Video Understanding) and CrewAI?

You assign roles. One agent uses analyzesync to segment the video, and another agent immediately calls embedasync on those segments. The MCP Server handles this handoff seamlessly for your crew.

Q: What is the best way to manage multiple videos with Twelve Labs (Video Understanding) and CrewAI?

Use createmultipartupload first. This manages the session for large files, allowing your autonomous operation to process dozens of videos in sequence without failing.

Run autonomous video intelligence teams with CrewAI's specialized agents.

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 CrewAI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate content embedding and indexing

You can set up an entire pipeline where one agent handles the raw analysis while another performs the data preparation. Use `embed_async` to generate embeddings for all video segments. The second step is using `index_asset`, which takes those rich vectors and stores them in a searchable index, making the knowledge immediately available.

Manage complex entity collections

The agents can collaborate to identify specific elements—like people or products—and group them using `create_entity`. They'll then store these groups using `create_entity_collection`. This allows for sophisticated, multi-step reporting: 'Find all instances of Person X and report on the associated objects.'

Retrieve indexed video data

Once everything is stored in an index, retrieving it is simple. You can use `get_index` to verify the structure or call `get_indexed_asset` directly. This means your autonomous crew doesn't need human intervention to pull specific facts out of the video database.

Setup guide

Set up Twelve Labs (Video Understanding) MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Twelve Labs (Video Understanding) tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Twelve Labs (Video Understanding) Analyst",
    goal="Access and analyze Twelve Labs (Video Understanding) data via MCP.",
    backstory="Expert analyst with direct Twelve Labs (Video Understanding) access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Twelve Labs (Video Understanding) transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Twelve Labs (Video Understanding) Analyst",
        goal="Access and analyze Twelve Labs (Video Understanding) data via MCP.",
        backstory="Expert analyst with direct Twelve Labs (Video Understanding) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Twelve Labs (Video Understanding) transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You assign roles. One agent uses `analyze_sync` to segment the video, and another agent immediately calls `embed_async` on those segments. The MCP Server handles this handoff seamlessly for your crew.

Absolutely. You can set up a dedicated monitoring agent that periodically calls `list_indexes` and `get_index` to verify that the data pipeline is running correctly and nothing has stalled.

The server handles raw video content, embeddings, asset metadata, indexed records, and structured entity collections. The crew directs which type to focus on.

Use `create_multipart_upload` first. This manages the session for large files, allowing your autonomous operation to process dozens of videos in sequence without failing.

The server processes video content, embeddings, indices, and entities. All access is controlled by the endpoint token provided to your multi-agent system.

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