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

Q: How does LlamaIndex index my Grocy (Home ERP) stock levels?

The framework uses the MCP tool spec to pull data from getstock and converts the JSON output into document nodes. These nodes are then embedded and stored in your vector database for quick semantic search.

Q: Can I query my Grocy (Home ERP) recipes semantically using LlamaIndex?

Yes, your agent can index all recipes returned by getrecipes. When you ask for a quick dinner, LlamaIndex searches the index, checks ingredient availability, and suggests recipes you can actually make.

Index your Grocy pantry data into LlamaIndex vector stores to query your kitchen inventory with zero hallucinations.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground your kitchen RAG with LlamaIndex and live stock

This Grocy MCP Server allows LlamaIndex to build a searchable knowledge base of your physical pantry. Instead of guessing what is in your cabinets, your agent retrieves live data using `get_stock` and indexes it directly into your vector store. When you ask what to cook, the agent queries this index to find matching ingredients. This approach stops your agent from hallucinating ingredients you do not own. It matches your queries against the actual details returned by `get_product` so your meal plans are always realistic.

Build a searchable archive of chores and tasks

Keep your household history organized by indexing your chore logs directly into LlamaIndex. Your agent pulls your completed activities via `get_chores` and tasks through `get_tasks`, turning them into searchable documents. You can then query your system to find out when the fridge was last cleaned. When a task is updated or finished, the agent runs `update_task` or `execute_chore` and updates the index. This ensures your search index always mirrors the physical state of your house.

Smart shopping lists powered by LlamaIndex RAG

This MCP Server lets your agent cross-reference your shopping lists with historical consumption patterns. The agent checks current needs using `get_shopping_list` and compares them against past stock updates. If it notices you buy milk every Tuesday, it can run `add_shopping_list_item` ahead of time. If you purchase items, the agent cleans up the database by running `remove_purchased_shopping_list`. Your vector store stays clean because the agent indexes the fresh, updated list immediately after.

Setup guide

Set up Grocy (Home ERP) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Grocy (Home ERP) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Grocy (Home ERP) tools.",
)
response = await agent.run("List recent Grocy (Home ERP) data")

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 LlamaIndex

The framework uses the MCP tool spec to pull data from `get_stock` and converts the JSON output into document nodes. These nodes are then embedded and stored in your vector database for quick semantic search.

Yes, your agent can index all recipes returned by `get_recipes`. When you ask for a quick dinner, LlamaIndex searches the index, checks ingredient availability, and suggests recipes you can actually make.

You can use the allowed tools filter when setting up your tool specification. This lets you restrict your agent to harmless tools like `get_stock` while blocking destructive tools like `clear_shopping_list`.

Yes, the agent parses your request, finds the right chore ID, and executes `execute_chore`. It then updates its local index so your search results reflect that the chore is done.

Your shopping list items and task details are processed through a secure Vinkius V8 sandbox. Only the text chunks your agent needs to index are sent to your local vector store, keeping your personal shopping habits private.

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