Medium Risk

curie_cart_aggregate_add

Add a line to the caller's aggregated multi-merchant cart with UPSERT-increment semantics — re-adding the same (shop_domain, product_variant_id) increments the existing line's quantity instead of inserting a duplicate row. The cart row is auto-created on first add (find-or-create on identity). Id...

Part of the Curie Commerce server.

curie_cart_aggregate_add can modify Curie Commerce data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE CURIE COMMERCE →

Free to start. No card required.

AI agents use curie_cart_aggregate_add to create or modify resources in Curie Commerce. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call curie_cart_aggregate_add repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Curie Commerce.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "curie_cart_aggregate_add": {
      "limits": [
        {
          "counter": "curie_cart_aggregate_add_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Curie Commerce policy for all 29 tools.

Get this rule live on your own Curie Commerce server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY CURIE COMMERCE →

View all 29 tools →

These attack patterns abuse exactly the kind of access curie_cart_aggregate_add gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so curie_cart_aggregate_add only ever does what you allow.

SECURE CURIE COMMERCE →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the curie_cart_aggregate_add tool do? +

Add a line to the caller's aggregated multi-merchant cart with UPSERT-increment semantics — re-adding the same (shop_domain, product_variant_id) increments the existing line's quantity instead of inserting a duplicate row. The cart row is auto-created on first add (find-or-create on identity). Identity is resolved from the request: Authorization: Bearer <jwt> for authed users, X-Curie-Device-Id (or the session device-id) for anon (matches /api/v1/aggregated-cart REST contract). Free / device-scoped — persists the cart anonymously like the wishlist; the actual purchase happens later at checkout.. It is categorised as a Write tool in the Curie Commerce MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on curie_cart_aggregate_add? +

Register the Curie Commerce MCP server in PolicyLayer and add a rule for curie_cart_aggregate_add: 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 Curie Commerce. Nothing to install.

What risk level is curie_cart_aggregate_add? +

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

Can I rate-limit curie_cart_aggregate_add? +

Yes. Add a rate_limit block to the curie_cart_aggregate_add 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 curie_cart_aggregate_add completely? +

Set action: deny in the PolicyLayer policy for curie_cart_aggregate_add. 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 curie_cart_aggregate_add? +

curie_cart_aggregate_add is provided by the Curie Commerce MCP server (https://chat.curie.app/api/mcp/global). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Curie Commerce tool call.

Deterministic rules across all 29 Curie Commerce tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.