How to Use the Mitto MCP in Pydantic AI

Q: How do I add the Mitto MCP Server to a Pydantic AI agent?

Install the package using pip install "pydantic-ai-slimmcp". Pass the Mitto server's URL to MCPToolset and include it in the toolsets list when initializing your Pydantic AI Agent.

Q: Does Pydantic AI support both HTTP and SSE transports for this MCP Server?

Yes, the Pydantic AI MCPToolset supports both Streamable HTTP and SSE transports for Mitto. You must run the Mitto server externally and point your toolset configuration to the running instance's endpoint.

Q: How do I track Mitto SMS campaign costs safely within Pydantic AI?

Your Pydantic AI agent calls getsmsusagebycountry to fetch regional billing data from Mitto. The framework validates the cost metrics against Pydantic models, allowing your application to safely calculate budget limits.

Q: How is my user's Mitto SMS message content secured during Pydantic AI transmission?

All message data sent via sendsms is encrypted in transit to the Mitto API. Vinkius runs the Mitto server in an isolated V8 sandbox, preventing any caching or leakage of your SMS text payloads.

Build type-safe messaging pipelines in Pydantic AI with strict runtime validation for Mitto SMS and 2FA tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mitto MCP to Pydantic AI

Create your Vinkius account to connect Mitto 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 Mitto with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validated 2FA workflows in Pydantic AI

The `send_2fa` tool dispatches Mitto verification codes with strict Pydantic AI type validation on the phone number format. If this MCP Server returns unexpected data, Pydantic AI raises a validation error immediately to prevent silent failures. Your Pydantic AI agent verifies the user's input using `verify_2fa` and checks usage history through Mitto's `get_2fa_usage`. Every returned Mitto data point conforms to your Pydantic AI schemas, keeping your authentication loop secure.

Structured bulk messaging with this MCP Server

The `send_bulk_sms` tool allows your Pydantic AI agent to send structured Mitto messages to multiple recipients. Pydantic AI validates your recipient lists and message parameters before hitting the Mitto API. You can track conversion rates using Mitto's `track_sms_conversion` without Pydantic AI parsing raw, untyped JSON responses. Pydantic AI guarantees that every Mitto delivery status update matches your defined data models.

Strongly typed anonymous routing

The `create_masking_context` tool spins up private Mitto routing environments for sensitive Pydantic AI workflows. Your Pydantic AI agent adds participants using `add_masking_participant`, with all parameters validated at runtime. If a participant's phone number is malformed, the Pydantic AI validation layer catches it before calling Mitto's `add_masked_number`. This prevents Mitto API errors and keeps your Pydantic AI communication channels clean.

Setup guide

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

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

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

Install the package using `pip install "pydantic-ai-slim[mcp]"`. Pass the Mitto server's URL to `MCPToolset` and include it in the `toolsets` list when initializing your Pydantic AI `Agent`.

The Pydantic AI framework raises a validation error immediately rather than letting your agent hallucinate parameters. This guarantees that data from Mitto tools like `lookup_number` is clean and correctly formatted before use.

Yes, the Pydantic AI `MCPToolset` supports both Streamable HTTP and SSE transports for Mitto. You must run the Mitto server externally and point your toolset configuration to the running instance's endpoint.

Your Pydantic AI agent calls `get_sms_usage_by_country` to fetch regional billing data from Mitto. The framework validates the cost metrics against Pydantic models, allowing your application to safely calculate budget limits.

All message data sent via `send_sms` is encrypted in transit to the Mitto API. Vinkius runs the Mitto server in an isolated V8 sandbox, preventing any caching or leakage of your SMS text payloads.

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