How to Use the Tavus Video Replicas MCP in CrewAI

Q: Can I audit my content history using Tavus Video Replicas and crewai?

Absolutely. By running listgeneratedvideos, your crew gets a complete record of assets. You can then use getvideodetails on any ID to pull all the metadata needed for a full content audit.

Run autonomous marketing campaigns with Tavus Video Replicas using your agent crew.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Tavus Video Replicas MCP to CrewAI

Create your Vinkius account to connect Tavus Video Replicas to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Tavus Video Replicas with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Design multi-stage video pipelines

A full campaign run starts by having an agent research content needs, which then calls `list_replicas` to find the right voice. Next, another specialized agent uses `get_replica_details` to confirm that replica's fidelity before initiating the final step. The core operation is running the generation via `generate_replica_video`. This tool allows your crew to hand off a complex task—generating personalized AI videos—and then track its completion using status checks.

Audit and govern content lifecycles

The first agent in the crew can run `list_generated_videos` to pull an inventory of all assets. A second, 'Moderator' agent then uses this list to determine what needs attention. It can call `get_video_details` on specific IDs for auditing purposes. If a video is outdated or unauthorized, the crew can use `delete_video` and subsequently run `delete_replica` if that voice model is no longer needed anywhere.

Discover all available resources via MCP Server

To kick off any process, your initial agent should always call `list_replicas`. This immediately gives the crew a list of every potential voice. It's faster than manually checking documentation. If you need to find out what videos have been created over time, running `list_generated_videos` is the simple command that provides an immediate inventory for your entire multi-agent operation.

Setup guide

Set up Tavus Video Replicas 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 Tavus Video Replicas tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Tavus Video Replicas 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="Tavus Video Replicas Analyst",
        goal="Access and analyze Tavus Video Replicas data via MCP.",
        backstory="Expert analyst with direct Tavus Video Replicas access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Tavus Video Replicas 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 Tavus. 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 Tavus Video Replicas 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 Tavus Video Replicas MCP in CrewAI

A crew can structure this as a sequence: Agent A lists replicas, Agent B gets details for the best candidate replica, and finally, the workflow triggers `generate_replica_video`. The tools work together to manage the complexity.

Absolutely. By running `list_generated_videos`, your crew gets a complete record of assets. You can then use `get_video_details` on any ID to pull all the metadata needed for a full content audit.

The server manages video job status, specifically tracking the `generation_status`. This is vital because it tells your autonomous agents when a piece of content is ready for use or if the process failed.

The most efficient method involves listing all videos, identifying old ones, and then calling `delete_video` for each one. You can follow this up by deleting any associated replicas using `delete_replica`.

The MCP Server is designed for autonomous pipelines. Since the tools are typed and defined, your agents can call them predictably, making complex, multi-step operations highly stable.

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