How to Use the Shipday MCP in LlamaIndex

Q: How does Shipday and LlamaIndex handle tracking updates?

You run gettrackingprogress, and the resulting status is indexed. Your agent can then query this index later to understand the historical path of a delivery, not just the current status.

Q: Can I compare multiple order details with Shipday and LlamaIndex?

Yes. By running getorder for several IDs, you can feed all those results into the index. Then, your agent can perform a semantic comparison across all stored records.

Q: What if I need to list and then query multiple orders with Shipday and LlamaIndex?

First, use listactiveorders. Next, index the data returned. The agent can then answer questions about the entire batch of listed IDs using semantic search.

Q: Does Shipday and LlamaIndex help with driver scheduling information?

You run listdrivers and store that list. Your client can then query this index to find specific capacity or availability details from past dispatch cycles.

Q: What data does Shipday and LlamaIndex handle regarding privacy?

The server handles customer details when you use createorder and the resulting order status via updateorderstatus. All this PII gets indexed, so index access must be tightly controlled.

Build knowledge-augmented Shipday systems using LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Shipday MCP to LlamaIndex

Create your Vinkius account to connect Shipday to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Shipday with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Query historical dispatch and order data.

LlamaIndex allows you to index all results from `get_order` or `list_active_orders`. Later, instead of re-running the API call, your agent performs a semantic search against that indexed data. You can ask complex questions about past deliveries. This builds a knowledge graph around your live API calls, letting you query outcomes and configurations from previous sessions.

Build documentation from driver assignments.

When you use `assign_driver`, the output is indexed. This means if someone asks, 'Who was assigned to order 123 last week?', LlamaIndex can retrieve that specific piece of API data and present it as a grounded answer. It transforms raw tool outputs into searchable knowledge base articles for your users.

Analyze multiple tracking progress reports.

If you run `get_tracking_progress` several times, LlamaIndex stores those time-series results. You can then query these stored records to find patterns—like 'When does the delivery usually slow down?'—without needing a dedicated analytics tool. It treats live operational data like historical documents.

Setup guide

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

You run `get_tracking_progress`, and the resulting status is indexed. Your agent can then query this index later to understand the historical path of a delivery, not just the current status.

Yes. By running `get_order` for several IDs, you can feed all those results into the index. Then, your agent can perform a semantic comparison across all stored records.

First, use `list_active_orders`. Next, index the data returned. The agent can then answer questions about the entire batch of listed IDs using semantic search.

You run `list_drivers` and store that list. Your client can then query this index to find specific capacity or availability details from past dispatch cycles.

The server handles customer details when you use `create_order` and the resulting order status via `update_order_status`. All this PII gets indexed, so index access must be tightly controlled.

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