AI agents use manage_purchases to commit financial operations through Kit — usually the final step of a payment, billing, or trading workflow. A call moves real money.
The tool explicitly supports creating/recording purchases, which represents a financial transaction or obligation. Even if it's recording rather than processing payment directly, committing financial records can have downstream billing, reporting, or compliance implications. The 'list' and 'get' actions are benign reads, but the 'create' action elevates this to Financial per severity hierarchy.
From the tool's definition 'record a new purchase' and action 'create' — this tool commits financial records/obligations by creating purchase entries in the email marketing platform
Attacks that exploit this kind of access
Manage Kit purchases — list, get details, or record a new purchase. Requires OAuth authentication. Actions: list, get, create. It is categorised as a Financial tool in the Kit MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Kit MCP server in PolicyLayer and add a rule for manage_purchases: 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 Kit. Nothing to install.
manage_purchases is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the manage_purchases 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 manage_purchases. 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.
manage_purchases is provided by the Kit MCP server (@dancumberland/kit-mcp). 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 →