create_cart

SERVERShop SOURCEhttps://mcp.tabak-brucker.de/mcp

Medium RISK CLASS

Category Write

Parameters 11 required

Recommended Rate-limitedsee the rule below

Registry record Grade C, identity unverified Pull the record →

This record as markdown: /tools/de-tabak-brucker-www-shop/create-cart.md

WHAT IT DOES

What create_cart does on Shop

AI agents use create_cart to create or update resources in Shop, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Shop environment.

Parameter	Type	Required	Description
`items`	array	Yes	Positionen (max. 50).

Parameters from the server's own tool schema.

RISK

Why create_cart is rated Medium

An AI agent can call create_cart faster than any human can review: one bad instruction and it creates or modifies resources in Shop by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs create_cart safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Shop, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For create_cart, this is the rule to start with:

create_cart Rate-limited

create_cart stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_cart": {
      "limits": [
        {
          "counter": "create_cart_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Shop, apply this rule, and every create_cart call is checked against it from then on.

FAQ

Questions about create_cart

What does the create_cart tool do? +

Legt einen vorbereiteten Warenkorb an und gibt eine Checkout-URL zurueck. WICHTIG: schliesst KEINE Bestellung ab — der Kunde muss die URL im Browser oeffnen und dort Login, Altersnachweis und Zahlung durchlaufen. It is categorised as a Write tool in the Shop MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does create_cart accept? +

create_cart accepts 1 parameter: items. Required: items. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on create_cart? +

Register the Shop MCP server in PolicyLayer and add a rule for create_cart: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Shop. Nothing to install.

What risk level is create_cart? +

create_cart is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_cart? +

Yes. Add a rate_limit block to the create_cart rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block create_cart completely? +

Set action: deny in the PolicyLayer policy for create_cart. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides create_cart? +

create_cart is provided by the Shop MCP server (https://mcp.tabak-brucker.de/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Shop, and thousands of servers like it.

This server

All 19 Shop tools →

Across the catalogue

create_task on 0rca Dojo MCP Server →create-task on Kanban MCP Server →create_package_backup on Android Forensics ADB MCP Server →create_project on Stitch MCP Server → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →