How to Use the Frontegg MCP in Pydantic AI

Q: What's the setup for the Frontegg MCP Server with Pydantic AI?

It's simple. After you pip install, you just instantiate the MCPToolset with your Vinkius server URL. Then you pass that toolset into your Pydantic AI Agent constructor, and all the Frontegg tools are ready to go.

Build type-safe identity agents with Pydantic AI to manage Frontegg users and tenants with guaranteed data correctness.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Frontegg MCP to Pydantic AI

Create your Vinkius account to connect Frontegg 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 Frontegg with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Tenants with Validated Data

This toolset gives your agent direct control over the Frontegg tenant lifecycle. You can provision new tenants with `create_tenant`, inspect them with `get_tenant_details`, and remove them with `delete_tenant`. It's a simple, direct API for account management. But with Pydantic AI, you get a critical guarantee. Every response from these tools is automatically parsed against a strict data model. If the Frontegg API ever returns an unexpected field for a tenant, your agent will raise a `ValidationError` instead of processing bad data.

Correct-by-Construction User Management

Manage your user base with confidence. Your agent can use `create_user`, `delete_user`, and `get_user_details` to handle user provisioning. The functions are straightforward and map directly to the core actions you need. Here's the key: Pydantic AI ensures that every user object your agent receives is valid. The raw JSON from a tool like `get_user_details` is instantly validated against a Pydantic model. This eliminates a whole class of bugs caused by unexpected API changes or malformed data.

Model-Driven Permission Audits

Build reliable auditing and reporting agents. The `list_permissions` and `list_system_roles` tools give your agent complete visibility into the roles and permissions configured in your Frontegg account. Because Pydantic AI validates every response, you can write agent logic that depends on the exact structure of a permission object without any defensive code. No more checking if a key exists in a dictionary. Your agent's code becomes cleaner because the data is guaranteed to be correct.

Setup guide

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

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

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

It's all about runtime data validation. Pydantic AI wraps the Frontegg MCP server's tools, and every single response is parsed against a strict Pydantic model. If the data from the API doesn't match the model, your code fails immediately and loudly.

It's simple. After you `pip install`, you just instantiate the `MCPToolset` with your Vinkius server URL. Then you pass that toolset into your Pydantic AI `Agent` constructor, and all the Frontegg tools are ready to go.

Yes, Pydantic AI is model-agnostic. You can use OpenAI, Anthropic, Gemini, or even a local LLM to power your Frontegg agent. You get the same type-safety and data validation guarantees regardless of the model you choose.

Your Pydantic AI agent will catch it. The first time the agent receives a response that doesn't fit its Pydantic model, it will raise a `ValidationError` that tells you exactly what went wrong. This prevents silent failures and data corruption.

Your agent will handle user and tenant identity data, like names, emails, and assigned roles. Pydantic AI processes this data in-memory to perform its validation checks. The actual connection to the MCP Server is secured by your Vinkius token, with each operation running as an isolated, ephemeral transaction.

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