How to Use the Shipday MCP in AutoGen

Q: How does Shipday and AutoGen handle tracking updates?

You can have a 'Monitor Agent' repeatedly calling gettrackingprogress. A second 'Alert Agent' monitors the output, only escalating an issue if the status hasn't changed after five consecutive checks.

Q: Can I get multiple order details with Shipday and AutoGen?

You can assign a 'Query Agent' to call getorder for several IDs. A 'Summarization Agent' then compiles the findings into one coherent report, resolving contradictions between records.

Q: What if I need to list and then check multiple orders with Shipday and AutoGen?

The process starts with a List Agent running listactiveorders. This output is passed to a 'Review Agent' which uses the IDs to call getorder for each one, building a consensus report.

Q: Does Shipday and AutoGen help with driver information?

Absolutely. A 'Resource Allocation Agent' can use listdrivers to gather data, which is then debated by the 'Scheduling Agent' to confirm optimal deployment before any assignments are made.

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

The server touches customer details via createorder and order information through getorder. When building consensus, the agents must agree on how to mask or redact this PII.

Run Shipday dispatch decisions through multi-agent deliberation using AutoGen.

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 AutoGen

Create your Vinkius account to connect Shipday to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Debate optimal driver assignment strategies.

You can set up a system where one 'Logistics Agent' calls `list_drivers` and another 'Dispatch Agent' calls `assign_driver`. They then debate the best pairing based on available capacity, achieving consensus before action. This forces decision-making to pass through multiple viewpoints, improving reliability over single API calls.

Simulate order creation and review processes.

Use three agents: a 'Customer Agent' calls `create_order`, an 'Audit Agent' checks for missing fields (like required restaurant info), and a 'Compliance Agent' validates the structure. They debate if the order is ready to proceed. This structured disagreement ensures data integrity before committing records.

Resolve conflicts in active order status updates.

An 'Operations Agent' calls `update_order_status`. A separate 'Supervisor Agent' reviews the call, checking it against the current state retrieved by `get_order` before allowing the change. They negotiate the final, safe status update. This is crucial for preventing race conditions in high-volume last-mile dispatch.

Setup guide

Set up Shipday MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Shipday tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Shipday_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Shipday data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Shipday_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Shipday data")
    print(result.messages[-1].content)

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 AutoGen

You can have a 'Monitor Agent' repeatedly calling `get_tracking_progress`. A second 'Alert Agent' monitors the output, only escalating an issue if the status hasn't changed after five consecutive checks.

You can assign a 'Query Agent' to call `get_order` for several IDs. A 'Summarization Agent' then compiles the findings into one coherent report, resolving contradictions between records.

The process starts with a `List Agent` running `list_active_orders`. This output is passed to a 'Review Agent' which uses the IDs to call `get_order` for each one, building a consensus report.

Absolutely. A 'Resource Allocation Agent' can use `list_drivers` to gather data, which is then debated by the 'Scheduling Agent' to confirm optimal deployment before any assignments are made.

The server touches customer details via `create_order` and order information through `get_order`. When building consensus, the agents must agree on how to mask or redact this PII.

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