How do I get my Client ID and API Key for Frontegg?

Log in to the Frontegg Portal, select your workspace/environment, go to 'Environment Settings' > 'API Keys', and create a Vendor token to get your Client ID and API Key.

Does this support multi-tenant management?

Yes! The agent can list, create, and delete individual tenants (customer accounts) within your environment using the 'list_tenants' and 'create_tenant' tools.

Can I search for a user across all tenants?

Yes, use the 'list_users' tool and provide an exact 'email' parameter. The agent will search across all tenants in the environment to find the user profile.

Is it possible to view role permissions?

You can use the 'list_system_roles' to view all roles and the 'list_permissions' tool to see the granular permissions available for assignment.

Frontegg MCP Server for OpenAI Agents SDK 12 tools — connect in under 2 minutes

Name: Frontegg
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 12 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Frontegg through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Frontegg Assistant",
            instructions=(
                "You help users interact with Frontegg. "
                "You have access to 12 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Frontegg"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Frontegg MCP Server

Connect your Frontegg environment to any AI agent to automate your B2B SaaS identity management through the Model Context Protocol (MCP). Frontegg is a powerful user management and authentication platform designed specifically for modern SaaS applications. This MCP server enables you to manage multi-tenant architectures, provision new users, and audit security configurations directly through natural conversation.

The OpenAI Agents SDK auto-discovers all 12 tools from Frontegg through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Frontegg, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

Key Features

Tenant Orchestration — List all customer accounts (tenants), retrieve their configuration details, and programmatically create or delete tenants.
User Provisioning — Access your global user database, fetch detailed profiles across tenants, and instantly invite or remove users.
Role & Permission Discovery — List all system roles and granular permissions to audit your security and access control models.
M2M Token Management — Retrieve Machine-to-Machine tokens for specific tenants to simplify backend integrations.
Real-time Synchronization — Keep your identity and access management operations accessible to your AI assistant without leaving your primary workspace.
Secure Environment Access — Authenticate securely using Vendor Client ID and API Keys to perform administrative operations safely.

The Frontegg MCP Server exposes 12 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Frontegg to OpenAI Agents SDK via MCP

Follow these steps to integrate the Frontegg MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 12 tools from Frontegg

Why Use OpenAI Agents SDK with the Frontegg MCP Server

OpenAI Agents SDK provides unique advantages when paired with Frontegg through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Frontegg + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Frontegg MCP Server delivers measurable value.

Automated workflows: build agents that query Frontegg, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Frontegg, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Frontegg tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Frontegg to resolve tickets, look up records, and update statuses without human intervention

Frontegg MCP Tools for OpenAI Agents SDK (12)

These 12 tools become available when you connect Frontegg to OpenAI Agents SDK via MCP:

check_environment_status

Verify API connection

create_tenant

Create a new tenant

create_user

Provision a user

delete_tenant

Delete a tenant

delete_user

Remove a user

get_tenant_details

Get tenant metadata

get_user_details

Get user metadata

list_m2m_tokens

List machine tokens

list_permissions

List granular permissions

list_system_roles

g. Admin, Read-Only) available for assignment. List roles

list_tenants

List all tenants/accounts

list_users

List users globally

Example Prompts for Frontegg in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Frontegg immediately.

"List the first 10 tenants in our Frontegg environment."

"Find the user details for 'jane@example.com'."

"Create a new tenant named 'Stark Industries'."

Troubleshooting Frontegg MCP Server with OpenAI Agents SDK

Common issues when connecting Frontegg to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Frontegg + OpenAI Agents SDK FAQ

Common questions about integrating Frontegg MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.