How to Use the 99Minutos Express MCP in LlamaIndex

Q: Can I use LlamaIndex to search my past 99Minutos Express shipping orders?

Yes, that's exactly what it's for. As your agent uses listorders and getorder, LlamaIndex ingests the results. You can then ask questions like 'find all orders sent from our main warehouse last week'.

Q: Can I filter which 99Minutos tools my LlamaIndex agent can access?

Yes. The McpToolSpec supports an allowedtools filter. You can give an agent access to only gettracking and getorder for a read-only tracking bot, for example.

Index your 99Minutos Express data and build logistics RAG applications with LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 99Minutos Express MCP to LlamaIndex

Create your Vinkius account to connect 99Minutos Express 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 99Minutos Express with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Shipping Data into a Knowledge Base

Tool calls are no longer just one-and-done transactions. When your agent uses `list_orders` or checks `get_rates`, LlamaIndex can automatically index the results into a vector store of your choice. Your shipping history becomes a queryable asset. This creates a private knowledge base grounded in your actual operations. You can ask questions in plain English about past shipments, costs, and delivery times without needing to re-run API calls or dig through logs.

Query Your Logistics History

Once your data is indexed, you can ask complex questions. "What was our average shipping cost to Monterrey last quarter?" Your agent queries the indexed results from previous `get_rates` calls to find the answer. It's fast and doesn't hit the live API. This is the core of RAG. Your LlamaIndex application provides answers grounded in real, historical data from your 99Minutos account. It drastically reduces the chance of your agent making things up.

Build Smart RAG Tools with LlamaIndex

Combine real-time data with your indexed knowledge. An agent can get a live package location with `get_tracking`. Then, it can query its indexed history of all past deliveries to that same ZIP code to give a more accurate ETA. This MCP Server provides the live data source. LlamaIndex gives you the framework to merge that with historical context. You're not just getting data; you're building an understanding of your logistics patterns.

Setup guide

Set up 99Minutos Express 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 99Minutos Express 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 99Minutos Express tools.",
)
response = await agent.run("List recent 99Minutos Express 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 99Minutos App. 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 99Minutos Express 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 99Minutos Express MCP in LlamaIndex

Yes, that's exactly what it's for. As your agent uses `list_orders` and `get_order`, LlamaIndex ingests the results. You can then ask questions like 'find all orders sent from our main warehouse last week'.

It grounds the answers in data. When you ask about a past shipment, LlamaIndex performs a vector search on the indexed data from actual `get_order` calls. The answer comes from that data, not the LLM's general knowledge.

It's straightforward. You'll install the LlamaIndex MCP adapter, instantiate the client with your Vinkius endpoint, and then use `McpToolSpec` to load the tools into your agent.

Yes. The `McpToolSpec` supports an `allowed_tools` filter. You can give an agent access to only `get_tracking` and `get_order` for a read-only tracking bot, for example.

Vinkius handles the live API call in a secure sandbox. The output data—like order details, rate quotes, and tracking history—is then passed to LlamaIndex to be indexed. You control the vector database where this indexed data is stored, giving you full ownership.

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