How to Use the Amiibo MCP in Google ADK

Q: How do I initialize the Amiibo MCP Server in Google ADK?

Use StreamableHttpServerParameters with your Vinkius URL. Wrap that in McpToolset and supply it to your LlmAgent tools array.

Q: Can Google ADK agents filter Amiibo by type?

Yes, they can. The agent invokes listamiibos and specifies the type parameter to separate physical figures from NFC cards.

Q: Is it possible to restrict access to specific MCP Server tools?

You can pass a toolnames list to the toolset setup. This lets you expose specific endpoints while blocking broad queries.

Connect the complete Amiibo database to your Google ADK agents and feed Nintendo metadata directly into Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amiibo MCP to Google ADK

Create your Vinkius account to connect Amiibo 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 Amiibo with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Expose the Amiibo MCP Server to Gemini

Enterprise agents on Google Cloud need reliable external APIs. You initialize `McpToolset` with your Vinkius HTTP endpoint and pass it directly to `LlmAgent`. Gemini immediately understands how to query the Nintendo catalog. Long-context reasoning shines here. You can dump massive arrays from `list_amiibos` directly into the prompt. Gemini parses the entire dataset to answer complex questions about cross-series character releases without breaking a sweat.

Feed BigQuery with Nintendo data

Moving data from external sources into your GCP infrastructure usually requires custom scrapers. Now your agent does it natively. It can pull every known figure using `list_amiibo_series` and format the output for your data warehouse. Filtering happens at the tool level before data hits your pipeline. The agent calls `list_characters` or `list_game_series` to restrict the payload. You save tokens and processing time by only loading what you actually need.

Fetch exact NFC metadata

Broad searches are fine for discovery. Sometimes you need exact specifications. When a user scans an NFC tag, your agent takes that ID and runs `get_amiibo`. It returns the exact character, game, and release type. You can restrict which operations the agent sees using the `tool_names` filter. If you only want it checking timestamps, expose `get_last_updated` and hide the rest. Your architecture stays clean and predictable.

Setup guide

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

Use `StreamableHttpServerParameters` with your Vinkius URL. Wrap that in `McpToolset` and supply it to your `LlmAgent` tools array.

Yes, they can. The agent invokes `list_amiibos` and specifies the type parameter to separate physical figures from NFC cards.

Yes. Any Gemini model running through the ADK supports these operations. The model reads the tool descriptions and decides when to call `list_types` or specific ID lookups.

You can pass a `tool_names` list to the toolset setup. This lets you expose specific endpoints while blocking broad queries.

Vinkius manages auth at the endpoint level via a single token. Your requests run inside an ephemeral V8 Isolate Sandbox, ensuring your BigQuery and GCP credentials never leak into the tool execution environment.

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