How to Use the Kinde (Modern Authentication) MCP in Google ADK

Q: How do I set up the Kinde (Modern Authentication) MCP server with the Google ADK?

First, pip install google-adk. Then, create an McpToolset pointing to your Vinkius server URL. You pass this toolset into your LlmAgent constructor.

Q: Is it possible to restrict which Kinde (Modern Authentication) tools are exposed to my Google ADK agent?

You can. The McpToolset constructor accepts a toolnames filter. Just provide a list of the only tool names you want the agent to see, like 'getuser', 'listusers'.

Connect Gemini to Kinde with the Google ADK. Manage identity across your Google Cloud workflow, from BigQuery to Vertex AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kinde (Modern Authentication) MCP to Google ADK

Create your Vinkius account to connect Kinde (Modern Authentication) 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 Kinde (Modern Authentication) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync BigQuery Rows to Kinde Users

Stop exporting CSVs to onboard users. Your Gemini agent can read a list of new hires directly from a BigQuery table. It then calls `create_user` in Kinde for each person on the list. Gemini's huge context window is the real advantage here. The agent can hold the details for thousands of users in its context before it even starts making tool calls, letting it plan the entire batch operation efficiently.

Create Kinde Orgs from GCP Triggers

Link your Kinde tenant structure to your cloud infrastructure. Set up a trigger so that when a new Google Cloud project is created, it invokes your agent. The agent then calls `create_organization` to provision a matching workspace in Kinde. You can also have it pre-configure the new org. After creation, the agent can call `list_roles` and `update_user` to assign a default project owner, all in one automated flow.

Run Identity Audits in Vertex AI with this MCP Server

Use a Gemini agent inside a Vertex AI Notebook to query your entire Kinde instance. It can `list_organizations` and then loop through them, calling `list_users` for each one to build a complete map of your user base. The agent can write the results straight into a new BigQuery table. This gives your security team a powerful way to analyze user access patterns using familiar Google Cloud tools.

Setup guide

Set up Kinde (Modern Authentication) 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 Kinde (Modern Authentication) 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="Kinde (Modern Authentication)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Kinde (Modern Authentication) 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 Kinde. 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 Kinde (Modern Authentication) 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 Kinde (Modern Authentication) MCP in Google ADK

First, `pip install google-adk`. Then, create an `McpToolset` pointing to your Vinkius server URL. You pass this toolset into your `LlmAgent` constructor.

Yes. Your agent can read a file from a GCS bucket, parse the user data, and then use the `create_user` or `update_user` tools to sync those changes to Kinde.

You can. The `McpToolset` constructor accepts a `tool_names` filter. Just provide a list of the only tool names you want the agent to see, like `['get_user', 'list_users']`.

Vinkius handles it. You get a single, secure endpoint token for the MCP server. You put that URL into the `StreamableHttpServerParameters`, and the ADK takes care of the rest.

The server processes Kinde user data, including names and emails, along with organization and role information. Security is handled by Vinkius's zero-trust, ephemeral sandbox. Your agent connects via a single token, so you aren't managing raw Kinde API keys in your GCP environment.

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