How to Use the Frontegg MCP in Google ADK

Q: How do I connect my Google ADK agent to this Frontegg MCP Server?

You use the McpToolset class from the ADK. Just give it your Vinkius server URL via StreamableHttpServerParameters. The toolset makes all the Frontegg functions available to your Gemini agent.

Q: Can I limit which Frontegg tools my agent can use?

You can. The McpToolset constructor in the Google ADK accepts a toolnames filter. This lets you create specialized agents, like an auditor that only has access to read-only tools like listusers and listtenants.

Connect Google ADK agents to your Frontegg identity layer and manage B2B users on Google Cloud.

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 Google ADK

Create your Vinkius account to connect Frontegg to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Frontegg Tenants in GCP

Run tenant management directly from an agent deployed on Google Cloud. Your Gemini-powered agent can use tools like `create_tenant` and `get_tenant_details` to provision and inspect Frontegg accounts. This links your cloud environment directly to your identity provider. Here's the thing: with Google ADK, your agent can reason over huge datasets. Feed it a BigQuery table with 10,000 pending customer signups, and Gemini's long context allows it to plan and execute a corresponding `create_tenant` call for each one, handling variations in plans and configurations.

Sync Users with Your Cloud Data

This MCP Server turns your agent into a bridge between your data and your identity platform. When a new customer record appears in a BigQuery table or a message hits a Pub/Sub topic, your agent can trigger `create_tenant` and `create_user` in Frontegg automatically. This setup means you don't have to write and maintain custom integration code. The Google ADK agent, equipped with these Frontegg tools, becomes the glue. It watches your Google Cloud data sources and acts on them, keeping your user base in sync.

Automated Role and Permission Audits

Use an agent to keep your permissions in check. It can run `list_users`, `list_tenants`, and `list_permissions` to pull a complete snapshot of your current Frontegg security posture. The agent can then cross-reference this data against your company's policies. Because you're in the Google ecosystem, you can schedule this agent as a Cloud Function. Have it run nightly, compare the output of `list_permissions` against a golden copy of your roles stored in Cloud Storage, and log any discrepancies to Google Cloud Logging for review.

Setup guide

Set up Frontegg MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Frontegg tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Frontegg_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Frontegg tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You use the `McpToolset` class from the ADK. Just give it your Vinkius server URL via `StreamableHttpServerParameters`. The toolset makes all the Frontegg functions available to your Gemini agent.

Yes. Gemini's million-token context window lets an agent process very large and complex customer requirements. It can read a full onboarding spec, then execute a precise sequence of `create_tenant`, `create_user`, and permission-setting calls.

It connects your cloud data directly to your identity management. Your Google ADK agent can react to events in BigQuery or Pub/Sub to provision Frontegg users and tenants. This saves you from building and maintaining your own brittle integration services.

You can. The `McpToolset` constructor in the Google ADK accepts a `tool_names` filter. This lets you create specialized agents, like an auditor that only has access to read-only tools like `list_users` and `list_tenants`.

The server exposes user identity information like names, emails, and tenant IDs. Access is controlled by your Vinkius token. Each tool call, such as `get_user_details`, is an isolated, sandboxed operation that executes within Google Cloud's security model.

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