How to Use the Kargo MCP in AutoGen

Q: How do I connect AutoGen to Kargo?

Install the autogen-extmcp package. Initialize mcpservertools with a StreamableHttpServerParams pointing to your URL, then pass the tools directly into your AssistantAgent.

Q: Does AutoGen handle Kargo tool schemas automatically?

McpToolAdapter converts the JSON schemas into a format the agents understand. They know exactly what arguments to pass for a specific shipment lookup.

Build AutoGen agent teams that debate Kargo loading dock assignments before executing them.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kargo MCP to AutoGen

Create your Vinkius account to connect Kargo to AutoGen 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 Kargo with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate logistics updates

A routing agent proposes a dock assignment using `update_logistics`, but a safety agent intercepts the call. The safety agent runs `get_device_status` to check if the assigned bay has an active hardware fault. They argue. The routing agent pushes for speed, while the safety agent refuses to route freight to a broken gate. You get a consensus-driven decision instead of a blind API execution.

Cross-check Kargo MCP Server data

Your AutoGen setup can dedicate one agent purely to reading the environment. This observer agent constantly polls `list_facilities` and `list_devices` to maintain a live map of your warehouse capacity. When the primary dispatcher agent wants to assign a load, it asks the observer for clearance. The observer checks `list_shipments` to see if the yard is full. If congestion is too high, the agents negotiate a delayed arrival window.

Verify orders across agents

One agent handles carrier communication by pulling details via `get_carrier_info`. Another agent verifies the actual freight using `get_order` and `get_shipment`. If the carrier says they are picking up three pallets but the order only shows two, the agents flag the discrepancy. They refuse to sync the final payload logs until a human resolves the mismatch.

Setup guide

Set up Kargo 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 Kargo 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="Kargo_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Kargo 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="Kargo_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Kargo 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 Kargo. 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 Kargo 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 Kargo MCP in AutoGen

Install the `autogen-ext[mcp]` package. Initialize `mcp_server_tools` with a `StreamableHttpServerParams` pointing to your URL, then pass the tools directly into your `AssistantAgent`.

Yes. You can bind the MCP Server to specific agents in your chat. A planning agent might have read access, while only the execution agent holds the rights to sync updates.

`McpToolAdapter` converts the JSON schemas into a format the agents understand. They know exactly what arguments to pass for a specific shipment lookup.

They continue the conversation based on your max turns limit. You can configure the chat to require human input if they cannot reach a consensus on the routing.

Nobody outside your specific session. The server operates as a stateless proxy. When your agents query facility IoT hardware data, the connection terminates the moment the response is delivered, leaving zero residual data behind.

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