How to Use the Tavus Video Replicas MCP in LangChain

Q: How do I check the status of a video job using Tavus Video Replicas with LangChain?

After calling generatereplicavideo, you get a job ID. You then pass this ID to your agent, which repeatedly polls the necessary endpoints until the status changes from 'processing' to 'completed'. This is critical for reliable chaining.

Q: If I need to audit my usage of Tavus Video Replicas with LangChain, what tools help?

Use listgeneratedvideos to pull a full history. Then, you can use getvideodetails on any specific ID to retrieve the original script inputs and generation metadata.

Q: What if I want to change the source material for an existing video using Tavus Video Replicas with LangChain?

You first need to delete the old job record via deletevideo. Then, you re-run the entire process using a new script ID in the generatereplicavideo call. It's better to restart than patch.

Build multi-step video pipelines with LangChain and Tavus Video Replicas.

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 LangChain

Create your Vinkius account to connect Tavus Video Replicas to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain Generation Steps

You start by listing available replicas using `list_replicas`. Then, you pass the resulting replica ID to ``get_replica_details`` to check its specific capabilities. This output feeds directly into your next step: initiating a new video with `generate_replica_video`. It's all about sequencing. Your agent calls one tool, gets data, and immediately uses that data point—like the generated Video ID—to call the next required function in the chain.

Manage Content Lifecycle

Need to track what you've made? First, use `list_generated_videos` to pull all job IDs. If something went sideways or needs updating, check the details with ``get_video_details`` using a specific ID. This ensures your chain has accurate state information before proceeding. And if the video is garbage? No problem. You can wipe it clean entirely by calling `delete_video` on that job ID. It keeps your data pipeline clean and predictable.

Advanced Replica Control

The system gives you total control over your assets. Use ``list_replicas`` to see everything you've uploaded. If a replica is outdated or problematic, you can permanently remove it using `delete_replica`. This keeps the pool of available voices lean and reliable for your agent. This precise management lets your multi-step reasoning pipeline trust the inputs. You know exactly which replicas are active and ready to generate content.

Setup guide

Set up Tavus Video Replicas MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Tavus Video Replicas tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "tavus-video-replicas-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Tavus Video Replicas transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

After calling `generate_replica_video`, you get a job ID. You then pass this ID to your agent, which repeatedly polls the necessary endpoints until the status changes from 'processing' to 'completed'. This is critical for reliable chaining.

Absolutely. You can build pipelines where one tool output—like a specific video ID—becomes the input variable for another tool call, allowing your agent to manage content from start to finish.

Use `list_generated_videos` to pull a full history. Then, you can use `get_video_details` on any specific ID to retrieve the original script inputs and generation metadata.

You first need to delete the old job record via `delete_video`. Then, you re-run the entire process using a new script ID in the ``generate_replica_video`` call. It's better to restart than patch.

The server handles video job metadata, including replica IDs and script identifiers. Always remember that this generation metadata is what you are tracking.

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