How to Use the Memberstack MCP in Google ADK

Q: How do I add the Memberstack toolset to a Google ADK agent?

Initialize McpToolset with the Vinkius HTTP server parameters pointing to your endpoint. Pass this toolset into the tools list when creating your LlmAgent in Python.

Q: Can I limit the Memberstack tools exposed to Google ADK?

Yes, you can use the optional toolnames filter in the ADK toolset configuration. This lets you expose only getmember while hiding sensitive billing tools like listcoupons.

Connect Google ADK to Memberstack to let Gemini check subscription plans and query customer details in real time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Memberstack MCP to Google ADK

Create your Vinkius account to connect Memberstack 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 Memberstack with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Google ADK agents with Memberstack tools

Enterprise agents running on Google Cloud need access to your actual user accounts. By mounting this MCP Server, your Google ADK agents can call `get_member` and `list_members` to pull active user profiles directly into Gemini's context window. This links your cloud backend directly to your user directory. The Google ADK makes this simple by letting you register the Vinkius HTTP endpoint as an `McpToolset`. Once loaded, your agent parses the schema, knows exactly when to query the server, and uses the returned member data to personalize its reasoning.

Map subscription tiers to Google Cloud pipelines

If you store analytical data in BigQuery, your Google ADK agent can match those records against live Memberstack subscription tiers. The agent uses `get_plan` and `list_plans` to verify what features a user has paid for before processing their cloud workflow. Using the Google ADK, you pass the toolset to your `LlmAgent`. Gemini can then read a user ID from a BigQuery row, call the Memberstack tools to check their plan, and decide if they qualify for high-priority computing resources.

Resolve billing queries with long-context reasoning

Gemini's massive token limit lets Google ADK ingest entire catalogs of promotion data. Your agent can run `list_promotions` and `list_coupons` to pull every active offer, processing the entire batch in a single turn to find the best discount for a user. The agent compares these deals against the user's current custom fields retrieved via `list_custom_fields`. It figures out the best upgrade path without relying on complex hardcoded logic in your Python application.

Setup guide

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

Initialize `McpToolset` with the Vinkius HTTP server parameters pointing to your endpoint. Pass this toolset into the `tools` list when creating your `LlmAgent` in Python.

Yes, you can use the optional `tool_names` filter in the ADK toolset configuration. This lets you expose only `get_member` while hiding sensitive billing tools like `list_coupons`.

Yes, the ADK supports both transports. For Vinkius cloud-hosted environments, you will use the `StreamableHttpServerParameters` to establish a secure HTTP connection.

Gemini uses its reasoning capabilities to look at the tools returned by the MCP Server. If a user asks about their billing, Gemini automatically invokes `get_member_plans` to fetch their active subscriptions.

All plan IDs and custom fields retrieved from the API are kept inside a secure, isolated V8 sandbox on Vinkius. This prevents external data leakage and ensures that credentials are never exposed to Google's training models.

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