How to Use the Tavus Video Replicas MCP in Pydantic AI

Q: How do I initiate video generation with Tavus Video Replicas using Pydantic AI?

Call generatereplicavideo(scriptid). Since the response is validated by Pydantic, you'll get a predictable object containing the new job ID. This prevents runtime errors.

Q: What if I need to check replica details with Tavus Video Replicas and Pydantic AI?

The getreplicadetails tool pulls all metadata for a specific replica, returning it in a strongly typed model. This means you can trust the data structure completely.

Q: How do I manage my video history with Tavus Video Replicas and Pydantic AI?

Use listgeneratedvideos to pull a list of all job records. The resulting JSON is validated against your schema, so you never have to worry about unexpected fields.

Q: Can I delete content safely with Tavus Video Replicas and Pydantic AI?

Absolutely. Calling deletevideo or deletereplica executes the action while maintaining type safety on the API calls, giving you confidence in data integrity.

Q: What data does the MCP Server touch when handling Tavus Video Replicas and Pydantic AI?

The server deals with replicaids, video job records, and script metadata. Every interaction is validated against defined models, making the process inherently safe.

Build type-safe video pipelines using the Pydantic AI framework 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 Pydantic AI

Create your Vinkius account to connect Tavus Video Replicas to Pydantic AI — 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Reliably Generate Videos with Type Safety

Generating a replica video needs solid data. Use `generate_replica_video` to initiate the process from a specific script ID. Because this is an MCP Server, the Pydantic framework validates every input and output payload, guaranteeing correctness.

Audit and Delete Media Assets

Need to clean up or verify assets? The agent can call `delete_video` for removal, or use `get_replica_details` to get a structured dump of replica information. This prevents silent data corruption.

Get Full Lists of Video and Replicas

Start by calling `list_replicas` to see all available voices, or `list_generated_videos` to pull a clean record of every video job. These tools ensure your agent always works with validated, up-to-date lists.

Setup guide

Set up Tavus Video Replicas MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "tavus-video-replicas-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Tavus Video Replicas tools.",
)

result = await agent.run("List recent Tavus Video Replicas transactions")
print(result.output)

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 Pydantic AI

Call `generate_replica_video(script_id)`. Since the response is validated by Pydantic, you'll get a predictable object containing the new job ID. This prevents runtime errors.

The `get_replica_details` tool pulls all metadata for a specific replica, returning it in a strongly typed model. This means you can trust the data structure completely.

Use `list_generated_videos` to pull a list of all job records. The resulting JSON is validated against your schema, so you never have to worry about unexpected fields.

Absolutely. Calling `delete_video` or `delete_replica` executes the action while maintaining type safety on the API calls, giving you confidence in data integrity.

The server deals with `replica_id`s, video job records, and script metadata. Every interaction is validated against defined models, making the process inherently safe.

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