How to Use the Dyte MCP in Pydantic AI

Q: Does this Dyte integration support the deprecated HTTP client in Pydantic AI?

No. You should use the unified MCPToolset class with your Vinkius HTTP URL to load the tools into your agent.

Build type-safe video integrations with Dyte and Pydantic AI to guarantee runtime schema correctness.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dyte MCP to Pydantic AI

Create your Vinkius account to connect Dyte 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 Dyte with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Session Creation and Management

The `create_meeting` tool runs through Pydantic AI's strict validation layer to ensure all meeting parameters match your exact schema. If the model attempts to pass malformed arguments, the framework catches it before hitting the API. Your code remains clean because tools like `add_participant` and `get_meeting` return strongly-typed objects that your agent parses without runtime surprises.

Strict Recording Controls via MCP Server

The `start_recording` tool works alongside `stop_recording` with strict type signatures that prevent corrupted configurations. Your agent can safely control archives knowing that Pydantic AI validates every payload. The same validation applies to livestream tools, where `start_livestream` and `stop_livestream` execute only if the target URLs and session IDs are perfectly formed.

Validated Participant and Webhook Audits

The `list_participants` tool returns clean, structured data lists that match your internal Python models. This allows your agent to run reliable validation checks on active users without parsing messy, unpredictable JSON. You can also deploy `create_webhook` to track session events, feeding the structured payloads directly into your backend validation pipelines.

Setup guide

Set up Dyte 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": {
        "dyte-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Pydantic AI will raise a validation error immediately. This prevents your agent from operating on corrupted or incomplete meeting payloads.

No. You should use the unified `MCPToolset` class with your Vinkius HTTP URL to load the tools into your agent.

Yes. Because Pydantic AI is model-agnostic, you can connect any local or cloud model to the Dyte tools via the external Vinkius MCP endpoint.

Pass the storage parameters dictionary directly through the tool call. Pydantic AI validates the structure against the MCP tool schema before sending it.

All API authorization tokens and participant join credentials are encrypted in transit. The MCP Server never persists session keys, routing them directly between your Pydantic AI application and Dyte.

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