How to Use the Mav MCP in Pydantic AI

Use Pydantic AI to enforce strict type safety on every SMS lead interaction handled by the Mav MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mav MCP to Pydantic AI

Create your Vinkius account to connect Mav 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 Mav with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe interactions in Pydantic AI

Every response from Mav gets validated against your Pydantic models at runtime. If the server sends unexpected data, your agent crashes before it can act on bad info. This prevents silent failures in your lead qualification pipeline. You define the schema, and the agent ensures Mav adheres to it every single time.

Unified toolset for Pydantic AI

The MCPToolset provides a clean, modern way to attach Mav to your agent. It replaces outdated connection methods to keep your codebase maintainable. You can point your agent at an external Mav server using SSE or HTTP. The framework handles the low-level communication so you can focus on writing better playbooks.

Model-agnostic SMS automation

Your agent can switch between different LLM backends without changing the Mav integration. Pydantic AI keeps the logic stable regardless of the underlying model. This is ideal if you want to test different models for your SMS qualification. The type-checking ensures that no matter which model you pick, the Mav tool calls remain consistent.

Setup guide

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

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

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

Define a Pydantic model for the expected response. The framework automatically validates incoming data from the Mav MCP server against this model.

Yes. Use the MCPToolset class for a unified connection approach. It supports both SSE and HTTP transports for maximum reliability.

The agent throws a validation error immediately. This stops the process and prevents your system from acting on corrupted lead information.

You can. The framework is model-agnostic, allowing you to use local or cloud-based LLMs while keeping the same Mav tool definitions.

Pydantic AI keeps your data isolated by running validation logic in your local process. Your SMS lead identifiers are never shared with the MCP server host, maintaining strict data integrity.

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