How to Use the Ezus MCP in LlamaIndex

Q: How does LlamaIndex prevent hallucinations when reading Ezus data?

LlamaIndex indexes the output of listproducts and listsuppliers into vector storage. The agent only answers queries using this verified data, ensuring high accuracy.

Q: How do I filter which tools my agent can access?

Use the allowedtools filter when initializing the client. You can restrict your agent to read-only tools like getproject and listprojects if you want to block write actions.

Build a searchable knowledge base of your travel agency data by connecting LlamaIndex to the Ezus MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ezus MCP to LlamaIndex

Create your Vinkius account to connect Ezus 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 Ezus with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Ezus client profiles for semantic search

The `list_clients` tool retrieves your complete customer list so LlamaIndex can index their profiles into a local vector store. Your agent queries this index using natural language to find matching travelers instead of performing manual keyword searches. This approach avoids database lookups for simple questions. You ask your agent which clients traveled to France last year, and it queries the vector database using the cached output of `get_client`.

Ground your LlamaIndex agent in live supplier data using MCP

The `list_suppliers` tool pulls active vendor records directly into your LlamaIndex RAG pipeline. When drafting an itinerary, the agent calls `get_supplier` to verify contact details and booking terms against your live database. By anchoring your agent in real-time data, you stop hallucinated pricing or outdated contact info from reaching your clients. The agent matches supplier contracts with active projects automatically.

Query invoice histories with LlamaIndex

The `list_invoices` tool feeds billing history directly into your query engine to resolve payment status questions. The agent calls `get_invoice` to pull line items and payment terms, generating accurate financial summaries for your management team. You don't have to write custom SQL queries to find unpaid accounts. The agent reads the parsed invoice data, matches it with client records, and lists outstanding balances instantly.

Setup guide

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

LlamaIndex indexes the output of list_products and list_suppliers into vector storage. The agent only answers queries using this verified data, ensuring high accuracy.

Yes. You connect the server using BasicMCPClient and convert the tools to a tool spec. This lets your LlamaIndex agents search live projects and client histories.

Use the allowed_tools filter when initializing the client. You can restrict your agent to read-only tools like get_project and list_projects if you want to block write actions.

Install llama-index-tools-mcp and instantiate the client with your Vinkius HTTP endpoint. Pass the tools to your FunctionAgent to start querying projects and clients.

Yes. Vinkius runs the server in an isolated, zero-trust environment. Your client names, emails, and project details retrieved via get_client are never cached or exposed to third parties.

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