Add charge to cart
AI agents use cart_add_charge to create or update resources in MCP Dynamics 365 Commerce Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Dynamics 365 Commerce Server environment.
Adding a charge to a cart is a write operation that modifies cart state. It is reversible (charges can typically be removed), so it's Write rather than Destructive. While it involves financial amounts, it does not move money or commit financial obligations — it only stages a charge in a cart prior to checkout, so Financial does not apply. Misuse could lead to incorrect charges being applied to customer orders.
From the tool's definition 'Add charge to cart' — creates/modifies cart data by adding a financial charge entry
Attacks that exploit this kind of access
Add charge to cart. It is categorised as a Write tool in the MCP Dynamics 365 Commerce Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Dynamics 365 Commerce Server MCP server in PolicyLayer and add a rule for cart_add_charge: 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 MCP Dynamics 365 Commerce Server. Nothing to install.
cart_add_charge is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the cart_add_charge 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.
Set action: deny in the PolicyLayer policy for cart_add_charge. 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.
cart_add_charge is provided by the MCP Dynamics 365 Commerce Server MCP server (jiantmo/mcp-commerce). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →