How to Use the Logto (Auth Platform) MCP in Google ADK

Q: Can I restrict Google ADK to specific Logto (Auth Platform) endpoints?

Yes, you apply the optional toolnames filter when instantiating your toolset. This lets you restrict the MCP tools exposed to Gemini, hiding destructive actions like deleteuser while allowing safe ones.

Q: How are sensitive user profiles and email addresses kept secure?

All user profile fields fetched via getuser or updated through updatemyaccountprimaryemail remain within your VPC boundaries. The server processes these payloads using ephemeral environments, preventing data from being stored in Google training sets.

Handle enterprise identity and B2B tenant lifecycles within Google ADK using Gemini long-context reasoning models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Logto (Auth Platform) MCP to Google ADK

Create your Vinkius account to connect Logto (Auth Platform) 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 Logto (Auth Platform) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise Directory Sync via Google ADK

`list_users` processes massive user directories by feeding batch records directly into Gemini's million-token context window. The Google ADK agent analyzes existing profiles and flags anomalies against historical data stored in BigQuery. Updates flow back to your identity tenant using `update_user` to keep profiles synchronized. Your agent runs these operations in parallel, matching cloud IAM states with your customer-facing directory.

B2B Organization Management at Scale

`list_organization_users` maps complex enterprise hierarchies within your agentic workflows. This MCP Server allows your Gemini agent to inspect corporate memberships and cross-reference them with Google Cloud storage buckets. When onboarding a new enterprise client, the agent invokes `create_organization` to spin up isolated resources. It then associates administrative roles using `list_roles` to complete the tenant environment.

Self-Service Security Workflows

`get_my_account` retrieves the active profile details so the agent can personalize the user interface. Google ADK routes these profile queries through secure vertex endpoints to verify session integrity. Users modify their security settings using `update_my_account_password` and `update_my_account_profile` directly through conversational prompts. The agent handles validation, ensuring no malformed payloads reach your identity platform.

Setup guide

Set up Logto (Auth Platform) 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 Logto (Auth Platform) 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="Logto (Auth Platform)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Logto (Auth Platform) 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 Logto. 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 Logto (Auth Platform) 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 Logto (Auth Platform) MCP in Google ADK

You initialize the connection using McpToolset with the HTTP transport parameters pointing to your hosted MCP Server. The ADK maps the identity tools directly into the Gemini model tool-calling interface.

Yes, you apply the optional tool_names filter when instantiating your toolset. This lets you restrict the MCP tools exposed to Gemini, hiding destructive actions like `delete_user` while allowing safe ones.

Gemini's long context allows the agent to ingest the entire payload of `list_resources` and `list_roles` simultaneously. It reasons over your entire authorization schema in a single pass without pagination lag.

Yes, the MCP Server supports both connection methods. For production deployments on Vertex AI, we recommend using the HTTP transport to maintain stateless, scalable agent execution.

All user profile fields fetched via `get_user` or updated through `update_my_account_primary_email` remain within your VPC boundaries. The server processes these payloads using ephemeral environments, preventing data from being stored in Google training sets.

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