How to Use the MRPeasy MCP in AutoGen

Q: How do I give my AutoGen agents access to MRPeasy tools?

Use the autogen-extmcp extension. The mcpservertools function takes your Vinkius server URL and returns a list of tool functions. You then pass this list directly to your AssistantAgent constructor.

Q: Do I need to manually handle the tool schemas for AutoGen?

No, the McpToolAdapter handles it for you. It automatically converts the MCP tool definitions into a format that AutoGen's agents can use for function calling. You just provide the URL.

Let your AutoGen agents debate and manage your MRPeasy production and inventory data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MRPeasy MCP to AutoGen

Create your Vinkius account to connect MRPeasy 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 MRPeasy with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Set Up a Multi-Agent Operations Team

Go beyond single-agent execution. With AutoGen, you can create a team of specialist agents that collaborate using MRPeasy data. For example, a 'LogisticsAgent' can monitor inventory using `list_stock_items` and propose a new purchase order when stock is low. Then, a 'FinanceAgent' can interject, using `list_purchase_orders` and `list_invoices` to check if the purchase fits the current budget. They converse, challenge each other's data, and arrive at a decision that balances operational needs with financial constraints. It's decision-making, not just data fetching.

Debate Production Schedules

Scheduling is full of trade-offs. Let your agents figure it out. One agent, the 'Planner', can use `list_manufacturing_orders` to create an optimal schedule. Another agent, the 'FloorSupervisor', can use `list_work_stations` to argue that a machine is overloaded. They can go back and forth, pulling data with tools like `get_manufacturing_order` to analyze specific jobs, until they reach a consensus schedule. You get to watch the entire conversation and see the logic behind the final plan. This MCP Server provides the facts for their debate.

Automate Supply Chain Analysis with AutoGen

Give your agents the tools to perform a complete supply chain analysis. One agent can be tasked with finding all customer orders over $10,000 using `list_customer_orders`. It passes that list to a second agent, which checks the production status for each using `get_manufacturing_order`. A third agent could then use `list_vendors` to check lead times for any required components that are out of stock. The final report is a product of collaboration, with each agent contributing its specialized analysis. The MRPeasy MCP server is their shared source of truth.

Setup guide

Set up MRPeasy 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 MRPeasy 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="MRPeasy_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the `autogen-ext[mcp]` extension. The `mcp_server_tools` function takes your Vinkius server URL and returns a list of tool functions. You then pass this list directly to your `AssistantAgent` constructor.

No, the `McpToolAdapter` handles it for you. It automatically converts the MCP tool definitions into a format that AutoGen's agents can use for function calling. You just provide the URL.

A solid pattern is a UserProxyAgent that takes your request, an 'InventoryAgent' that can call `list_stock_items`, and a 'ProductionAgent' that can call `list_manufacturing_orders`. They can then work together to answer complex questions about your operations.

Yes, that's exactly what it's for. You can equip multiple agents in an AutoGen `GroupChat` with the same or different sets of MRPeasy tools. They will be able to call these functions during their conversation to get data and prove their points.

The server accesses your core MRPeasy data: manufacturing orders, customer details, and stock items. Vinkius secures this with a zero-trust model where every tool call from your agent is authenticated. Your data is only processed for the duration of the request.

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