How to Use the Dynamic (Web3 Auth) MCP in Google ADK

Q: How do I register Dynamic (Web3 Auth) in a Google ADK project?

Initialize McpToolset using the HTTP parameters pointing to your Vinkius endpoint, then pass it to your LlmAgent tool list. This exposes the Web3 auth tools directly to your Gemini model.

Q: Can Google ADK filter which Dynamic (Web3 Auth) tools are exposed to Gemini?

Yes, you can pass an optional toolnames list to the toolset initialization to restrict exposure. This ensures your agent only accesses specific tools like checksanctions or gettokenbalances based on security policies.

Q: How does Gemini leverage Dynamic (Web3 Auth) data for BigQuery analytics?

Your Google ADK agent calls getuser to retrieve profile metadata, then formats and inserts that structured identity data directly into BigQuery. This bridges Web3 auth with enterprise data warehousing.

Q: What happens if an active session needs to be killed?

The agent can invoke revokesession to immediately end a user's active session. This allows your Google ADK workflows to respond to security events in real-time.

Run Web3 compliance checks and manage user profiles directly from your Google ADK pipelines using this managed MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dynamic (Web3 Auth) MCP to Google ADK

Create your Vinkius account to connect Dynamic (Web3 Auth) 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 Dynamic (Web3 Auth) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct Sanctions Checks in Google ADK

The `check_sanctions` tool runs automated wallet compliance checks inside your Google ADK runtime before processing off-chain actions. Your Gemini agent queries this endpoint to block restricted addresses before writing any transaction records to BigQuery. This direct verification loop keeps your analytical datasets clean. By filtering out non-compliant wallets early, you avoid polluting your enterprise data warehouse with tainted Web3 addresses.

Context-Rich Profile Queries

The `get_user` and `get_token_balances` tools fetch detailed Web3 metadata to feed Gemini's long-context window. Your agent analyzes user profiles alongside historical enterprise data to personalize financial recommendations. Because Gemini handles 1M+ tokens, you can feed entire user profiles and balance histories directly into the prompt. The MCP integration structures this data so your models make decisions based on real-time on-chain holdings.

Webhook Management via Google ADK MCP Server

The `get_webhooks` and `get_event_types` tools expose active auth notifications to your Google ADK workflows. Your agent monitors these endpoints to sync Web3 user sign-ins with your Google Cloud infrastructure. This setup connects your Web3 events directly to enterprise pipelines. You can trigger automated Cloud Functions or update Vertex AI models as soon as new wallet patterns are detected.

Setup guide

Set up Dynamic (Web3 Auth) 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 Dynamic (Web3 Auth) 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="Dynamic (Web3 Auth)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Dynamic (Web3 Auth) 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 Dynamic. 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 Dynamic (Web3 Auth) 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 Dynamic (Web3 Auth) MCP in Google ADK

Initialize `McpToolset` using the HTTP parameters pointing to your Vinkius endpoint, then pass it to your `LlmAgent` tool list. This exposes the Web3 auth tools directly to your Gemini model.

Yes, you can pass an optional `tool_names` list to the toolset initialization to restrict exposure. This ensures your agent only accesses specific tools like `check_sanctions` or `get_token_balances` based on security policies.

Your Google ADK agent calls `get_user` to retrieve profile metadata, then formats and inserts that structured identity data directly into BigQuery. This bridges Web3 auth with enterprise data warehousing.

The agent can invoke `revoke_session` to immediately end a user's active session. This allows your Google ADK workflows to respond to security events in real-time.

All profile metadata and wallet addresses queried via this MCP Server are processed in memory within Vinkius's zero-trust sandbox. No personal data is written to persistent logs unless your Google ADK agent explicitly writes it to your cloud database.

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