Low Risk

get_cart

Inspect the current state of a cart — line items, quantities, prices, and shipping address. Each item includes an item_id you can pass to update_cart_item to change quantity or remove the item. Call this after add_to_cart to review the cart before checkout, or any time the buyer asks what's in th...

Part of the Kifly — Agentic Commerce & Payments server.

get_cart is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE KIFLY — AGENTIC COMMERCE & PAYMENTS →

Free to start. No card required.

AI agents call get_cart to retrieve information from Kifly — Agentic Commerce & Payments without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though get_cart only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_cart": {}
  }
}

See the full Kifly — Agentic Commerce & Payments policy for all 18 tools.

Get this rule live on your own Kifly — Agentic Commerce & Payments server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY KIFLY — AGENTIC COMMERCE & PAYMENTS →

View all 18 tools →

These attack patterns abuse exactly the kind of access get_cart 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 get_cart only ever does what you allow.

SECURE KIFLY — AGENTIC COMMERCE & PAYMENTS →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the get_cart tool do? +

Inspect the current state of a cart — line items, quantities, prices, and shipping address. Each item includes an item_id you can pass to update_cart_item to change quantity or remove the item. Call this after add_to_cart to review the cart before checkout, or any time the buyer asks what's in the cart.. It is categorised as a Read tool in the Kifly — Agentic Commerce & Payments MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_cart? +

Register the Kifly — Agentic Commerce & Payments MCP server in PolicyLayer and add a rule for get_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 Kifly — Agentic Commerce & Payments. Nothing to install.

What risk level is get_cart? +

get_cart is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_cart? +

Yes. Add a rate_limit block to the get_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 get_cart completely? +

Set action: deny in the PolicyLayer policy for get_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 get_cart? +

get_cart is provided by the Kifly — Agentic Commerce & Payments MCP server (https://kifly.ai/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Kifly — Agentic Commerce & Payments tool call.

Deterministic rules across all 18 Kifly — Agentic Commerce & Payments 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.