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

Get your LangChain agents to manage your pantry and chores by linking Grocy MCP tools into your active reasoning chains.

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 LangChain

Create your Vinkius account to connect Grocy (Home ERP) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build automated recipe and stock chains in LangChain

This Grocy MCP Server lets your LangChain agents run multi-step kitchen logistics. First, your agent calls `get_recipes` to see what you can cook. Then, it hooks into `get_stock` to check if you actually have the ingredients on hand. If anything is missing, the chain moves to the next link and appends the missing items using `add_shopping_list_item` without you lifting a finger. You can track the entire execution in LangSmith to see exactly how your agent made the decision. If a recipe run fails, you will see if it choked on `consume_recipe` or if the stock levels were just off. This gives you a clear view of your household data flow.

Coordinate smart chore and task sequences

Managing a house means keeping chores and tasks in sync, which is easy when your LangChain ReAct agent handles the schedule. The agent checks what needs cleaning by running `get_chores` and matches it against your active workload using `get_tasks`. Once a chore is done, the agent triggers `execute_chore` to update your database. Because LangChain supports multi-server aggregation, you can link this MCP Server to your calendar API. Your agent can look at your free time, pick a chore, and write a new task via `create_task` to block out your afternoon.

Maintain physical battery rotations in LangChain

This MCP Server exposes tools to keep your household devices powered up without constant manual checks. Your agent queries your device states using `get_batteries` to find which ones are dead. It then links that data to your shopping workflow, letting the chain run `add_shopping_list_item` if you are out of spares. When you finally plug a device in, the agent runs `charge_battery` to reset the timer. LangSmith traces every step of this battery rotation, letting you audit how often your devices drain and when they get swapped.

Setup guide

Set up Grocy (Home ERP) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Grocy (Home ERP) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "grocy-home-erp-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Grocy (Home ERP) transactions"
    })
    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 LangChain

Install the adapter package using pip and initialize the client with your Vinkius endpoint. You then pass the tools from `client.get_tools()` directly into your agent constructor to let it access your pantry data.

Yes, you can build a chain that takes a meal name, looks up the ingredients with `get_recipe`, and runs `consume_recipe` to update your pantry. The output of the recipe check feeds right into the stock subtraction tool.

LangSmith logs every single tool run, showing you the exact inputs sent to `add_product_stock` or `inventory_product_stock`. If your agent tries to add the wrong quantity, you can pinpoint the exact step where the chain went wrong.

Yes, the connection is stateless by default, making it easy to run inside serverless environments. If you need to keep context across multiple household updates, use the session helper to maintain state.

Your pantry stock levels and chore logs remain sandboxed within the Vinkius V8 execution environment. The LangChain agent only accesses the API to run tools like `get_stock`, and no raw household data is stored on external servers.

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