How to Use the Authing MCP in Google ADK

Q: How do I initialize the Authing MCP Server with Google ADK?

Instantiate an McpToolset using your Vinkius endpoint URL inside StreamableHttpServerParameters. Then pass that toolset directly into your LlmAgent configuration array.

Q: Can I filter which Authing tools Google ADK exposes?

Yes, just provide a list of allowed strings to the toolnames argument. This prevents the Gemini model from seeing or calling createuser if you only want a read-only security agent.

Feed Authing MCP Server identity data directly into your Google ADK agents for deep IAM analysis using Gemini's massive context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Authing MCP to Google ADK

Create your Vinkius account to connect Authing 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 Authing with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery integration for Authing MCP Server

Enterprise teams pull thousands of records using `list_users` and pipe them straight into Google Cloud infrastructure. Your Gemini agent grabs the current IAM state and immediately joins it with historical access data sitting in BigQuery. Running `get_audit_logs` through the ADK lets the model process massive security event timelines. Because Gemini handles millions of tokens, the agent reads the entire raw JSON output without chunking or losing context.

Vertex AI security analysis

Hooking up `get_security_settings` allows your Google agents to evaluate pool configurations against Vertex AI threat models. The framework natively understands the toolset responses and feeds them into your custom reasoning loops. Developers restrict the exposed operations by passing a `tool_names` filter to the `McpToolset` constructor. Limiting the agent to `list_organizations` and `list_applications` ensures it maps infrastructure but doesn't modify it.

Mapping complex groups with Gemini

Cloud administrators use `list_groups` and `list_roles` to untangle messy permission structures. The ADK takes that relational data and builds a clear picture of who holds what access across your entire enterprise. Pulling `list_resources` gives the LLM the exact boundaries of your system. You just pass the Vinkius URL into `StreamableHttpServerParameters` and the agent starts querying your identity provider instantly.

Setup guide

Set up Authing 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 Authing 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="Authing_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Authing 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 Authing. 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 Authing 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 Authing MCP in Google ADK

Instantiate an `McpToolset` using your Vinkius endpoint URL inside `StreamableHttpServerParameters`. Then pass that toolset directly into your `LlmAgent` configuration array.

Yes, just provide a list of allowed strings to the `tool_names` argument. This prevents the Gemini model from seeing or calling `create_user` if you only want a read-only security agent.

The framework handles HTTP transport natively. Your agent communicates with the remote MCP Server endpoint without needing local proxy servers.

The ADK relies on the massive context window of Gemini 1.5 Pro to ingest giant payloads. Calling `list_users` on a huge directory works perfectly because the model reads the entire list at once.

Vinkius routes your requests through an ephemeral, zero-trust sandbox that leaves no trace. Sensitive IAM payloads like `get_user` profiles flow straight to your Google Cloud environment and never persist on our infrastructure.

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