How to Use the Grocy (Home ERP) MCP in AutoGen

Q: Can AutoGen agents debate which Grocy (Home ERP) recipes to cook?

Yes, one agent can pull recipes using getrecipes and check current stock with getstock. Another agent can debate the nutritional value before they agree to run consumerecipe.

Let your AutoGen agents debate household chores and pantry shopping to find the most efficient way to run your home.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Grocy (Home ERP) MCP to AutoGen

Create your Vinkius account to connect Grocy (Home ERP) 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 Grocy (Home ERP) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve chore disputes with AutoGen agent debates

This Grocy MCP Server enables multi-agent discussions about how to split up household work. You can set up one agent to advocate for chore completion and another to manage member schedules. They query `get_chores` to see what is overdue, negotiate who does what, and run `execute_chore` once they agree. This setup prevents single-agent errors and ensures chores are allocated fairly. The agents debate the urgency of each task using data from `get_tasks` before finalizing the schedule.

Budget and inventory negotiation via MCP Server

Managing a grocery budget is easier when your agents debate before shopping. A frugal agent can review your list using `get_shopping_list` while a meal-prep agent pushes for specific ingredients. They negotiate what to buy, then run `add_shopping_list_item` only for approved items. If they find duplicate or unnecessary items, they can run `clear_shopping_list` and rebuild it. This consensus-driven approach keeps your pantry stocked without overspending.

Coordinate complex stock transfers and consumption

This MCP Server gives your AutoGen agents the tools to manage items across multiple physical locations. When food is moved from the basement freezer to the kitchen, one agent logs the move with `transfer_product_stock`. A second agent verifies the target stock level using `get_product`. If the food is used, they cooperate to run `consume_product_stock`. This multi-agent verification loop keeps your digital inventory aligned with your actual physical pantry.

Setup guide

Set up Grocy (Home ERP) 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 Grocy (Home ERP) 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="Grocy (Home ERP)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Grocy (Home ERP) 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="Grocy (Home ERP)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Grocy (Home ERP) 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 Grocy. 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 Grocy (Home ERP) 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 Grocy (Home ERP) MCP in AutoGen

You use the AutoGen MCP extension to fetch the tools from your Vinkius HTTP endpoint. The adapter automatically translates the schemas so you can pass them directly to your `AssistantAgent` constructor.

Yes, one agent can pull recipes using `get_recipes` and check current stock with `get_stock`. Another agent can debate the nutritional value before they agree to run `consume_recipe`.

Yes, you can configure a guardrail agent to monitor tool calls. If an agent tries to execute `clear_shopping_list` without consensus, the system blocks the call before it modifies your database.

Yes, the adapter supports both stdio and streamable HTTP transports. This lets you run your household agents locally or host them on a remote server depending on your setup.

All communication with your Grocy instance is handled through an encrypted Vinkius endpoint. Your active task lists and chore execution logs are never exposed to public networks during agent debates.

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