How to Use the Inworld AI MCP in Pydantic AI

Q: How do I stream audio safely using this type-safe setup?

Your agent calls synthesizespeechstream to get a validated stream of audio bytes. Pydantic AI monitors the stream chunks to ensure they conform to the expected binary format.

Run type-safe voice synthesis and character routing in Pydantic AI with strict runtime validation over an MCP connection.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Inworld AI MCP to Pydantic AI

Create your Vinkius account to connect Inworld AI to Pydantic AI 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 Inworld AI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe voice cloning in Pydantic AI

The `clone_voice` tool creates custom voice profiles from audio samples with strict type-safety guarantees. Your Pydantic AI agent validates the input audio metadata against strict schemas before executing the clone action. If the server returns incomplete voice details, the agent raises a validation error immediately rather than passing corrupted data. You can safely manage these assets using `get_voice` and `delete_voice` without worrying about silent failures.

Validated routing schemas via MCP Server

The `create_router` tool defines character routing configurations that are verified at runtime. Your Pydantic AI agent uses `get_router` to inspect the router's structure, ensuring all fields match your expected Python models. This MCP Server setup prevents your agent from executing malformed routing updates. Any call to `update_router` must pass strict schema validation, protecting your production dialogue trees from corruption.

Verified text-to-speech and transcription

The `synthesize_speech_sync` tool converts text to speech while ensuring the output payload matches your exact data models. Your agent verifies the returned audio binary and metadata before delivering them to the client. When handling user audio, the agent runs `transcribe_audio` to get a structured text transcript. The framework validates the transcription response format instantly, guaranteeing clean input for your LLM.

Setup guide

Set up Inworld AI 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": {
        "inworld-ai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Inworld AI 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 Inworld AI. 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 Inworld AI 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 Inworld AI MCP in Pydantic AI

Initialize MCPToolset with your Vinkius HTTP URL and pass it to the Agent's toolsets parameter. The framework automatically wraps the 19 tools in type-safe schemas.

The agent will fail loudly with a validation error, preventing silent model corruption. This ensures your voice configurations remain completely accurate.

Yes, the toolset is completely model-agnostic. You can run voice synthesis and routing tools using Anthropic, Gemini, or local models.

Your agent calls `synthesize_speech_stream` to get a validated stream of audio bytes. Pydantic AI monitors the stream chunks to ensure they conform to the expected binary format.

Your voice profiles and audio files are processed inside isolated, ephemeral V8 sandboxes. Vinkius secures the transport layer, and Pydantic AI enforces strict data schemas to prevent injection attacks on your voice assets.

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