// SCAN REPORT

MCP Grocy API

37 tools. 11 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 11 Jun 2026

11 can modify or destroy data

26 read-only

37 tools total

Community server · catalogue entry verified 11/06/2026

How to control MCP Grocy API ↓

TOOL MAP

Read (26) Write / Execute (8) Destructive / Financial (3)

MOST DANGEROUS TOOLS

Critical Risk

Financial · Critical charge_battery Track charging of a battery in your Grocy instance. Financial · Critical transfer_product Transfer a product from one location to another in your Grocy instance. Destructive · High remove_shopping_list_item Remove an item from your shopping list. Write · Medium add_missing_products_to_shopping_list Add all missing products for a recipe to your shopping list.

11 of MCP Grocy API's 37 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL MCP GROCY API

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Grocy API, and nothing reaches the server without passing your rules. These are the rules we recommend:

Block financial tools by default

{
  "charge_battery": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Deny destructive operations

{
  "remove_shopping_list_item": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_missing_products_to_shopping_list": {
    "limits": [
      {
        "counter": "add_missing_products_to_shopping_list_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "call_grocy_api": {
    "limits": [
      {
        "counter": "call_grocy_api_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register MCP Grocy API — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP GROCY API →

Free to start. No card required.

ALL 37 MCP GROCY API TOOLS

FINANCIAL 2 tools

Financial charge_battery Track charging of a battery in your Grocy instance. Financial transfer_product Transfer a product from one location to another in your Grocy instance.

DESTRUCTIVE 1 tools

Destructive remove_shopping_list_item Remove an item from your shopping list.

WRITE 8 tools

Write add_missing_products_to_shopping_list Add all missing products for a recipe to your shopping list. Write add_recipe_products_to_shopping_list Add not fulfilled products of a recipe to the shopping list. Write add_recipe_to_meal_plan Add a recipe to the meal plan. Write add_shopping_list_item Add an item to your shopping list. Write complete_task Mark a task as completed in your Grocy instance. Write create_recipe Create a new recipe in your Grocy instance. Write inventory_product Track a product inventory (set current stock amount). Write open_product Mark a product as opened in your Grocy instance.

READ 26 tools

RELATED SERVERS

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Can an AI agent move money through the MCP Grocy API MCP server? +

Yes. The MCP Grocy API server exposes 2 financial tools including charge_battery, transfer_product. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

Can an AI agent delete data through the MCP Grocy API MCP server? +

Yes. The MCP Grocy API server exposes 1 destructive tools including remove_shopping_list_item. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through MCP Grocy API? +

The MCP Grocy API server has 8 write tools including add_missing_products_to_shopping_list, add_recipe_products_to_shopping_list, add_recipe_to_meal_plan. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach MCP Grocy API.

How many tools does the MCP Grocy API MCP server expose? +

37 tools across 4 categories: Destructive, Financial, Read, Write. 26 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on MCP Grocy API? +

Register the MCP Grocy API MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every MCP Grocy API tool call.

Deterministic rules across all 37 MCP Grocy API tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP GROCY API →

Free to start. No card required.

37 MCP Grocy API tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

MCP Grocy API

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL MCP GROCY API

// ALL 37 MCP GROCY API TOOLS

// RELATED SERVERS

// FAQ