How to Use the Katana MCP in AutoGen

Debate and decide manufacturing workflows using Katana MCP Server and AutoGen agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Katana MCP to AutoGen

Create your Vinkius account to connect Katana 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 Katana with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent debate for Katana orders

Assign one agent to `list_sales_orders` and another to `list_manufacturing_orders` to compare availability. They negotiate the best path forward for fulfillment. This conversation framework prevents errors by forcing agents to challenge each other's conclusions. You see the debate unfold in the logs.

Automated Katana workflows in AutoGen

Set your agents to use `create_sales_order` only after a consensus is reached between the sales and operations roles. It mimics a human approval process without the lag. Your system handles the delegation automatically. The agents verify their own work against the tool schemas before execution.

Katana MCP Server tool adapter

The adapter handles all schema conversions, letting your AutoGen agents call `list_suppliers` or `list_products` without manual mapping. Your agents focus on the logic, not the API structure. They receive the raw data and use it to drive the group's decision-making process.

Setup guide

Set up Katana 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 Katana 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="Katana_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the MCP extension and use the server parameters to point to your endpoint. Pass the resulting tool list directly into your AssistantAgent constructor.

Yes, you configure agents to debate based on conflicting data points. For example, an agent might flag a discrepancy between `list_materials` and current production demands.

The server supports both stdio and HTTP transports. You choose the one that fits your deployment architecture for the best performance.

You add more specialized agents to the conversation group to handle specific toolsets. This distributes the work across a larger pool of reasoning participants.

Your customer information is only shared between agents within your private conversation loop. No external parties or services have access to the data processed by the MCP server.

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