Close an order (mark as fulfilled/closed)
AI agents use close_order to create or update resources in Mcp Ap2 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Ap2 environment.
The tool modifies order data by changing its status from open to fulfilled/closed. While this is a significant operation in a financial payment context, it does not move money, create charges, or authorize payments (Financial category). It also does not irreversibly delete data (Destructive category).
From the tool's definition close_order marks an order as fulfilled/closed, which modifies the order status in the system. This is a write operation that changes order state reversibly (orders could theoretically be reopened).
Documented attack patterns abuse exactly the kind of access close_order gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for close_order:
{
"version": "1",
"default": "deny",
"tools": {
"close_order": {
"limits": [
{
"counter": "close_order_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}close_order 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.
Free to start. No card required.
Close an order (mark as fulfilled/closed). It is categorised as a Write tool in the Mcp Ap2 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for close_order: 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 Ap2. Nothing to install.
close_order 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 close_order 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 close_order. 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.
close_order is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Ap2, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
1300 Mcp Ap2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.