How to Use the Humanitix MCP in LlamaIndex

Q: Can LlamaIndex query Humanitix order history for semantic search?

Yes, your agent can call listorders to fetch purchase records and index them into a vector store. This allows users to ask conversational questions about order trends.

Q: Does the Humanitix toolset work with LlamaIndex query engines?

Yes. The output from tools like listhosts and getme can be converted into document nodes for indexing, making them searchable by any query engine.

Q: How does LlamaIndex handle live inventory updates from Humanitix?

Your agent runs listinventory dynamically during the conversation loop. This guarantees that the retrieved context contains the latest ticket counts before generating a response.

Index your Humanitix events and attendee logs directly into LlamaIndex vector stores for search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Humanitix MCP to LlamaIndex

Create your Vinkius account to connect Humanitix 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 Humanitix with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Event Schedules into Vector Stores

We query your event details using `list_events` and `list_venues` to build searchable vector databases. Your LlamaIndex pipeline ingests the raw JSON output, parses the venue addresses, and indexes them for semantic queries. This lets your agent answer complex location questions without hardcoded database lookups. You query past events based on natural language queries rather than exact matches. If a user asks for outdoor events, the index retrieves the corresponding data pulled from `get_event` automatically.

Feed the LlamaIndex MCP Server into RAG Pipelines

This MCP Server exposes `list_tickets` and `list_inventory` to supply your RAG applications with real-time ticket availability. The agent queries current counts, formats the response, and uses it to ground its answers. This prevents the LLM from hallucinating ticket prices or availability. By indexing this live feed, your agent can cross-reference ticket types with historical sales data. It makes decisions based on actual numbers, not outdated cache files.

Search Attendee Records Semantically

Your agent uses `list_attendees` via this MCP Server to pull guest profiles and feed them directly into your query engines. It vectorizes the attendee metadata, making it possible to search for specific groups of guests based on registration details. You avoid writing complex SQL queries just to filter your guest list. This workflow combines attendee lists with marketing metrics from `list_campaigns`. Your agent analyzes which campaigns drove the most registrations by cross-referencing both indexes.

Setup guide

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

Use the MCP tool spec package to create a basic client pointing to the server. Convert the client into tool specs and pass them to your FunctionAgent.

Yes, your agent can call `list_orders` to fetch purchase records and index them into a vector store. This allows users to ask conversational questions about order trends.

Yes. The output from tools like `list_hosts` and `get_me` can be converted into document nodes for indexing, making them searchable by any query engine.

Your agent runs `list_inventory` dynamically during the conversation loop. This guarantees that the retrieved context contains the latest ticket counts before generating a response.

Yes, the server acts as a direct bridge, and only the specific event descriptions, venue details, and ticket tiers you request are processed. Your data remains in your local index and is never stored on external servers.

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