How to Use the Aventri MCP in LlamaIndex

Q: How do I convert Aventri contact data into LlamaIndex documents?

You load the Aventri contact records using listcontacts and pass the JSON output directly to LlamaIndex's Document parser. This creates searchable LlamaIndex vector embeddings of your Aventri attendee details.

Q: Can I use LlamaIndex to search Aventri events semantically?

Yes, by indexing the output of Aventri's listevents and searchevents into a LlamaIndex vector store. Your LlamaIndex agent can then retrieve matching Aventri events based on conceptual descriptions rather than rigid text filters.

Q: How do I filter allowed tools like getspeaker in LlamaIndex?

You define an allowed tools list containing Aventri's getspeaker when initializing the LlamaIndex McpToolSpec. This limits your LlamaIndex agent to speaker lookups while blocking administrative tools like deletecontact.

Index Aventri event data and contact registries into LlamaIndex vector stores for semantic retrieval.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aventri MCP to LlamaIndex

Create your Vinkius account to connect Aventri 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 Aventri with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Aventri events into your LlamaIndex knowledge base

This MCP Server allows your LlamaIndex agent to query and index Aventri event structures using `list_events` and `search_events`. The retrieved Aventri event metadata is converted into LlamaIndex document nodes and stored directly in your vector database. Instead of running keyword matches, you can query your LlamaIndex index semantically to find similar past Aventri events. The LlamaIndex agent uses these indexed records to decide which templates to duplicate when running the Aventri `clone_event` tool for upcoming conferences.

Build RAG pipelines over Aventri attendee databases

LlamaIndex indexes raw Aventri contact data retrieved from `list_contacts` and `get_contact` to ground your agent's responses in real registration metrics. This prevents your LlamaIndex agent from hallucinating Aventri attendee details or registration statuses during queries. When you ask about specific registrants, the LlamaIndex system queries the vector store first, then uses `update_contact` or `add_contact` to modify Aventri records based on the latest verified data. This keeps your LlamaIndex vector store and Aventri database aligned.

Query speaker records using LlamaIndex agent tools

Your LlamaIndex FunctionAgent searches and indexes Aventri speaker profiles by calling `list_speakers` and `get_speaker` dynamically. The retrieved Aventri speaker bios and session topics are stored as searchable LlamaIndex vector embeddings. When planning new panel tracks, your LlamaIndex agent searches this index to find matching profiles before invoking the Aventri `create_speaker` tool. This LlamaIndex workflow reduces duplicate Aventri entries and speeds up agenda building.

Setup guide

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

You load the Aventri contact records using `list_contacts` and pass the JSON output directly to LlamaIndex's Document parser. This creates searchable LlamaIndex vector embeddings of your Aventri attendee details.

Yes, by indexing the output of Aventri's `list_events` and `search_events` into a LlamaIndex vector store. Your LlamaIndex agent can then retrieve matching Aventri events based on conceptual descriptions rather than rigid text filters.

Yes, your LlamaIndex agent can query the vector index to find discrepancies and immediately call Aventri's `update_contact` to correct them. This keeps your LlamaIndex vector store and live Aventri registration database synchronized.

You define an allowed tools list containing Aventri's `get_speaker` when initializing the LlamaIndex McpToolSpec. This limits your LlamaIndex agent to speaker lookups while blocking administrative tools like `delete_contact`.

Your Aventri attendee contact emails and speaker bios are indexed directly into your local LlamaIndex vector database. The Vinkius gateway handles the Aventri connection securely without caching or storing any of your indexed registration data.

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