How to Use the Clerk MCP in Google ADK

Q: How do I initialize the Clerk MCP server within Google ADK?

Import McpToolset from the ADK library and point it to your Vinkius streamable HTTP server URL. Then, pass the toolset into the LlmAgent constructor using the tools parameter. This makes all eight authentication tools instantly available to your Gemini model.

Q: Can I restrict which Clerk tools are exposed to Google ADK?

Yes, you can use the optional toolnames filter when defining your McpToolset. This allows you to restrict the agent's access to specific tools like listauthallowlist while hiding others. It keeps your enterprise agent focused on a narrow set of tasks.

Run deep analysis on your Clerk user directory using Gemini and the Google ADK framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clerk MCP to Google ADK

Create your Vinkius account to connect Clerk 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 Clerk with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run user directory queries inside Google ADK

`list_clerk_users` pulls your entire user directory into the Gemini long-context window for instant analysis. Your enterprise agent can cross-reference hundreds of user profiles against your BigQuery tables to identify sign-up trends. Using this MCP Server, your agent reads the directory state directly. It eliminates the need to export CSVs or write custom sync scripts to get user lists into your Google Cloud environment.

Monitor system health and active client devices

`get_auth_dashboard_summary` and `list_clerk_clients` let your agent track system health and device distribution. The agent checks these metrics to detect sudden spikes in new client registrations or system usage. You can feed this real-time telemetry into Vertex AI models for predictive scaling. Your agent handles the data retrieval, leaving your engineers free to focus on core infrastructure.

Manage B2B tenant structures with Gemini

`list_clerk_organizations` exposes your multi-tenant B2B structure to your Google ADK agent. The agent queries this tool to understand organization hierarchies, membership counts, and active domains. This setup enables automated tenant auditing. Your agent maps out organization structures and flags inactive workspaces without manual data mapping.

Setup guide

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

Import `McpToolset` from the ADK library and point it to your Vinkius streamable HTTP server URL. Then, pass the toolset into the `LlmAgent` constructor using the `tools` parameter. This makes all eight authentication tools instantly available to your Gemini model.

Yes, you can use the optional `tool_names` filter when defining your `McpToolset`. This allows you to restrict the agent's access to specific tools like `list_auth_allowlist` while hiding others. It keeps your enterprise agent focused on a narrow set of tasks.

Gemini's 1M+ token window allows your agent to ingest the entire JSON response from `list_clerk_users` at once. The model analyzes the complete user list in a single prompt, identifying patterns that shorter-context models would miss.

Yes, the ADK integration works with both transport protocols. Since Vinkius hosts and manages the server, you will typically use the HTTP transport to connect your Google Cloud agents to the hosted endpoint.

Your API tokens are isolated within the Vinkius MCP sandbox environment and are never exposed to the Google Cloud transport layer. The user emails, domain names, and session IDs retrieved by the server are passed directly to your agent in transit and are never cached or logged by Vinkius.

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