How to Use the Frontegg MCP in OpenAI Agents SDK

Q: What kind of user roles can my agent see?

Your agent can call listsystemroles to get the standard set of roles available in your Frontegg environment, like 'Admin' or 'Read-Only'. For more detailed control, listpermissions provides the granular permissions that make up those roles.

Provision and manage B2B tenants and users directly from your production agents with the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Frontegg to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage B2B Tenants from Your Agent

This toolset lets your agent handle the full tenant lifecycle inside Frontegg. You can spin up a new account with `create_tenant`, get its metadata with `get_tenant_details`, or remove it entirely using `delete_tenant`. It’s a direct line from your agent's logic to your identity infrastructure. Because you're using the OpenAI Agents SDK, you can add guardrails to these actions. For example, you can require human approval before an agent runs `delete_tenant` on a high-value account. The SDK's built-in tracing also gives you a full audit log of every tenant-related action your agent performs.

Provision Users and Assign Roles

Onboard new users without leaving your chat. Your agent can call `create_user` to provision a new seat in a specific tenant. You can also pull user information with `get_user_details` or remove them with `delete_user`. Pair these with `list_system_roles` and `list_permissions` to build complex onboarding flows. An agent can create a user, check available roles, and then assign the correct permissions, all in one sequence. With the OpenAI dashboard, you get a clear, step-by-step view of the entire process.

Audit Your Identity Infrastructure with an MCP Server

Give your agent the ability to run compliance checks and generate reports. It can `list_tenants` to get a complete picture of all accounts or use `list_users` to see every user in the system. For backend services, `list_m2m_tokens` shows all active machine-to-machine credentials. This is where the OpenAI Agents SDK's handoff feature shines. You could have one specialized agent that just queries data using these list functions, then hands the raw output to another agent designed to format it into a human-readable report or a CSV file.

Setup guide

Set up Frontegg MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Frontegg tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Frontegg tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Frontegg tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Frontegg Agent",
            instructions="You have access to Frontegg tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

It's designed for auto-discovery. Just pass the Vinkius MCP server endpoint to your agent. The OpenAI Agents SDK automatically finds all the available Frontegg tools like `create_tenant` and makes them callable.

The tools are atomic, so you'd have your agent loop through a list and call `create_tenant` for each one. The SDK's async support makes this process efficient, so it can run many concurrent requests without blocking.

Yes, it's safer than running manual scripts. The SDK has built-in guardrails that you can configure to prompt for human approval on sensitive operations. This lets an agent propose a permission change with `list_permissions` but requires your sign-off to execute it.

Your agent can call `list_system_roles` to get the standard set of roles available in your Frontegg environment, like 'Admin' or 'Read-Only'. For more detailed control, `list_permissions` provides the granular permissions that make up those roles.

This server handles user identity data, including names, emails, and tenant associations. Your connection is secured by a Vinkius endpoint token, and every operation runs in an ephemeral, zero-trust sandbox. The OpenAI agent only has access to the data it explicitly requests via tools like `get_user_details`.

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