How to Use the Mio MCP in Pydantic AI

Q: Does Pydantic AI validate the output of Mio tools?

Yes, every response from tools like getcalltranscript or getcreditbalance is validated against strict Pydantic models at runtime. If the server returns unexpected data, the framework raises a validation error immediately.

Q: Can my agent manage webhooks using Mio and Pydantic AI?

Your agent can programmatically manage webhooks using createwebhook, listwebhooks, and deletewebhook. Each operation is fully typed, ensuring your agent configures endpoints without syntax errors.

Execute type-safe voice calls and validate transcript data at runtime using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mio MCP to Pydantic AI

Create your Vinkius account to connect Mio 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 Mio with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe voice operations with Pydantic AI

`start_ai_call` initiates voice connections with strict runtime type-checking on all input parameters. If your agent attempts to pass an invalid phone number or a voice ID not found in `list_available_voices`, the framework blocks the call instantly. This prevents malformed API requests from consuming your budget. Integrating this MCP Server ensures that your voice agents operate with absolute mathematical correctness. You avoid silent failures during live calls, as the agent can verify the active status of a call or end it using `terminate_call` with fully validated payloads.

Strict transcript validation

`get_call_transcript` fetches the complete text log of your voice interactions, mapping the response directly to Pydantic models. Your agent parses this text with guaranteed structural integrity, ensuring that parsed entities like dates or dollar amounts match your exact schemas. If you only need a quick recap, `get_call_summary` returns a validated, structured overview. This strict schema enforcement eliminates the risk of hallucinated fields. Your downstream database operations can trust the output of your agent because every character has been validated against your defined Python types.

Account and webhook management

`get_account_info` retrieves your profile details, while `get_credit_balance` returns your remaining funds as a validated float. You manage real-time alerts by registering endpoints with `create_webhook`, listing active configurations with `list_webhooks`, and purging old ones with `delete_webhook`. These administrative tools allow your agent to monitor its own operational limits. It checks the MCP Server to pause outbound calling and alert your team before any service interruption occurs.

Setup guide

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

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

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

You install the slim MCP package and use the unified MCPToolset class pointing to your Vinkius HTTP endpoint. Pass this toolset directly to your Agent instance to enable all twelve validated tools.

Yes, every response from tools like `get_call_transcript` or `get_credit_balance` is validated against strict Pydantic models at runtime. If the server returns unexpected data, the framework raises a validation error immediately.

Your agent can programmatically manage webhooks using `create_webhook`, `list_webhooks`, and `delete_webhook`. Each operation is fully typed, ensuring your agent configures endpoints without syntax errors.

The framework supports both Streamable HTTP and SSE transports. You must run the MCP Server externally and connect your agent using the unified toolset initialization method.

All webhook URLs, credentials, and call logs are processed within ephemeral V8 isolates. Vinkius secures the MCP endpoints with zero-trust architecture, ensuring that sensitive routing data is never cached or leaked.

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