How to Use the Amilia MCP in LlamaIndex

Q: How do I configure the Amilia MCP server for LlamaIndex?

Install llama-index-tools-mcp and instantiate a BasicMCPClient with your endpoint URL. Convert the client using McpToolSpec and pass the resulting tools to your agent.

Q: Can LlamaIndex search through Amilia family contacts?

It does. You call listcontacts to pull the raw JSON, which the framework then embeds into your index for natural language querying.

Q: How do I restrict which Amilia tools my agent can run?

Use the allowedtools filter when setting up your McpToolSpec. This prevents the engine from calling getattendance if you only want it searching public program catalogs.

Q: Does this setup support data access via resources?

Yes. Setting includeresources=True allows the engine to read static configuration files exposed by the server, alongside the standard tool execution.

Index recreation programs and attendance data for semantic search using LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amilia MCP to LlamaIndex

Create your Vinkius account to connect Amilia 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 Amilia with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a searchable program index

The `list_programs` and `list_activities` tools feed raw catalog data from your MCP server directly into your vector store. LlamaIndex pulls the entire summer camp schedule and embeds it, turning a basic API response into a semantically searchable knowledge base. Users query your agent for "weekend pottery classes for kids" instead of exact ID matches. The framework retrieves the most relevant nodes from the indexed activity metadata and returns grounded answers.

Ground answers in real account data

You fetch specific user profiles using the `get_account_details` and `list_registrations` tools. LlamaIndex combines this structured API output with unstructured documents like your facility's waiver policies. When a parent asks about their upcoming schedule, the query engine checks the indexed registration data against the actual class times from `list_activity_occurrences`. This prevents the agent from hallucinating dates or mixing up different family accounts.

Query historical rosters via MCP Server

The `get_attendance` tool supplies the raw check-in records for your RAG application. You pull past session rosters, index them, and let your query engine analyze attendance patterns across different seasons. Integrating this requires minimal boilerplate. You wrap your `BasicMCPClient` with `McpToolSpec` and pass it to a `FunctionAgent`, instantly giving your index access to live recreation data.

Setup guide

Set up Amilia 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 Amilia 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 Amilia tools.",
)
response = await agent.run("List recent Amilia 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 Amilia. 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 Amilia 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 Amilia MCP in LlamaIndex

Install `llama-index-tools-mcp` and instantiate a `BasicMCPClient` with your endpoint URL. Convert the client using `McpToolSpec` and pass the resulting tools to your agent.

It does. You call `list_contacts` to pull the raw JSON, which the framework then embeds into your index for natural language querying.

Use the `allowed_tools` filter when setting up your `McpToolSpec`. This prevents the engine from calling `get_attendance` if you only want it searching public program catalogs.

Yes. Setting `include_resources=True` allows the engine to read static configuration files exposed by the server, alongside the standard tool execution.

Vinkius handles the transport layer through an ephemeral, zero-trust sandbox. Your query engine receives the registration histories, but the connection drops immediately after, ensuring no persistent backdoors to your family records.

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