How to Use the Duo Security (Two-Factor Authentication API) MCP in Pydantic AI

Q: Can I programmatically manage child accounts using the Duo Security (Two-Factor Authentication API) and Pydantic AI?

Yes, your agent can run createaccount and deleteaccount to manage MSP child environments. Every account object returned is fully validated against strict Python type hints using this MCP integration.

Q: What is the safest way to handle bulk user imports with Pydantic AI?

Your agent should use bulkcreateusers to register up to 100 profiles simultaneously. Pydantic AI validates the input array structure before sending the payload, preventing partial batch failures.

Secure your Pydantic AI workflows with type-safe, runtime-validated Duo Security identity controls.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Duo Security (Two-Factor Authentication API) MCP to Pydantic AI

Create your Vinkius account to connect Duo Security (Two-Factor Authentication API) 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 Duo Security (Two-Factor Authentication API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute runtime-validated `auth` operations

The `auth` tool initiates out-of-band authentication checks that return strictly typed responses to your Pydantic AI agent. Because every response matches a rigid schema validated by your MCP client, your agent won't execute downstream code on corrupted or partial data payloads. The agent monitors the transaction status by calling `auth_status` in a type-safe polling loop. If the response structure deviates even slightly from the expected schema, the framework raises a validation error immediately.

Type-safe user management via MCP Server tools

The `create_user` tool allows your agent to add new users while validating their username and email formats at runtime. This prevents malformed strings from reaching your Duo database and causing synchronization drift. If you need to modify existing profiles, `modify_user` applies patch updates with strict parameter validation. The agent ensures that only valid fields are sent, keeping your directory clean and structured.

Audit billing editions and telephony credits

The `get_billing_edition` tool retrieves the active subscription tier for your account, returning validated objects directly to your agent. This lets your system confirm feature availability before attempting administrative tasks. To prevent service disruptions, the agent calls `get_telephony_credits` to check your available balance. If the return integer falls below your safety threshold, the agent halts further phone-based authentication attempts.

Setup guide

Set up Duo Security (Two-Factor Authentication API) 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": {
        "duo-security-two-factor-authentication-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Duo Security (Two-Factor Authentication API) tools.",
)

result = await agent.run("List recent Duo Security (Two-Factor Authentication API) 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 Duo Security. 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 Duo Security (Two-Factor Authentication API) 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 Duo Security (Two-Factor Authentication API) MCP in Pydantic AI

The framework wraps every tool response in a Pydantic model, checking fields returned by tools like `preauth` or `list_users` at runtime. If the API returns unexpected fields or missing values, the system raises a validation error instantly.

Use the unified MCPToolset class pointing to your running server URL and pass it to your Agent constructor. This replaces the deprecated MCPServerHTTP class and provides instant access to tools like `ping_auth`.

Yes, your agent can run `create_account` and `delete_account` to manage MSP child environments. Every account object returned is fully validated against strict Python type hints using this MCP integration.

Your agent should use `bulk_create_users` to register up to 100 profiles simultaneously. Pydantic AI validates the input array structure before sending the payload, preventing partial batch failures.

Your integration keys, signatures, and user records are processed ephemerally in a secure V8 sandbox. No data is cached or logged outside your execution environment, keeping your administrative secrets completely isolated.

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