How to Use the Amiibo MCP in LlamaIndex

Q: How do I make my LlamaIndex agent fetch new Amiibo data only when the database has been updated?

Your agent should first call the getlastupdated tool. You can store that timestamp and compare it on subsequent runs. Only when the timestamp changes does the agent need to re-run listamiibos and update its index.

Q: What's the process for feeding the Amiibo listamiibos tool results into a LlamaIndex vector store?

After your agent calls listamiibos, you'll get a list of Amiibo objects. You can transform this list into LlamaIndex Document objects and then use a data ingest pipeline to add them to your chosen vector index.

Turn the Amiibo database into a searchable knowledge base for your LlamaIndex RAG apps. Ask questions, get answers grounded in real data.

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 LlamaIndex

Create your Vinkius account to connect Amiibo to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Amiibo Data for RAG

This server's tools feed directly into a LlamaIndex pipeline. Your agent doesn't just fetch Amiibo data; it indexes it. Run `list_amiibos` once, and the results are ingested into a vector store. Now your agent can answer questions about that data without hitting the API again. This lets you build a RAG application that combines the live Amiibo database with your own collection notes or public reviews. Your queries get smarter because they search across all that connected information at once, giving you answers with much deeper context.

Query Your Collection Semantically

Once the data from `list_amiibos` or `list_characters` is indexed, you can move beyond simple keyword filtering. You can ask your LlamaIndex agent questions like, 'show me figures with a 'monster' or 'villain' theme.' It finds related items based on meaning, not just exact text matches. This turns the Amiibo MCP Server into a long-term memory for your agent. You can query past results, compare different series you've looked up before, and get answers grounded in data you've already fetched and indexed. It's a persistent, searchable history of your interactions.

Ground Responses in API Facts

Stop agent hallucinations cold. When a user asks, 'Which Amiibo were released for Metroid Dread?', a LlamaIndex agent can be configured to first call `list_amiibos` with the `gameSeries` filter. The answer is built directly from that API output, not the model's memory. Using the `McpToolSpec`, you give your agent a clear manifest of what this MCP Server can do. It knows it can use `get_amiibo` to get release dates or `list_types` to see if a character has both a card and a figure. The answers are always tied to real, verifiable data.

Setup guide

Set up Amiibo MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Amiibo MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Amiibo tools.",
)
response = await agent.run("List recent Amiibo data")

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 LlamaIndex

Yes. First, get a list of your owned Amiibo IDs. Then, use the `get_amiibo` tool in a loop to fetch the data for each one and feed the results directly into your LlamaIndex vector store for semantic search.

Your agent should first call the `get_last_updated` tool. You can store that timestamp and compare it on subsequent runs. Only when the timestamp changes does the agent need to re-run `list_amiibos` and update its index.

After your agent calls `list_amiibos`, you'll get a list of Amiibo objects. You can transform this list into LlamaIndex `Document` objects and then use a data ingest pipeline to add them to your chosen vector index.

Absolutely. That's a core strength of LlamaIndex. You can index the data from the Amiibo tools alongside your own text files or PDFs. When you run a query, the agent will search across all indexed sources.

The MCP server itself doesn't store anything; it just fetches public Amiibo data (names, series, etc.) on demand. Your LlamaIndex application will store this data in your own vector database. The Vinkius connection is stateless and secured by your unique token.

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