Submit an order to Legiti for real-time fraud evaluation via the v2 order endpoint. Returns a decision (approve / reject / manual) synchronously — response may take up to ~20s. Include as much context as possible: account, payment (tokenized card bin+last4), CPF, billing/shipping, and for ticketi...
AI agents invoke evaluate_order to trigger actions in Mcp Ap2. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool submits data to an external fraud evaluation API and receives a binding decision that directly influences whether orders are approved or rejected. While it doesn't move money directly, it executes an external call with real operational consequences (approval/rejection of orders) that go beyond a simple read.
From the tool's definition 'Submit an order to Legiti for real-time fraud evaluation' — triggers an external synchronous operation against a third-party fraud evaluation service, with decisions (approve/reject/manual) that affect downstream order processing
Documented attack patterns abuse exactly the kind of access evaluate_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 evaluate_order:
{
"version": "1",
"default": "deny",
"tools": {
"evaluate_order": {
"limits": [
{
"counter": "evaluate_order_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}evaluate_order stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Submit an order to Legiti for real-time fraud evaluation via the v2 order endpoint. Returns a decision (approve / reject / manual) synchronously — response may take up to ~20s. Include as much context as possible: account, payment (tokenized card bin+last4), CPF, billing/shipping, and for ticketing flows the event_date_id / sale_items. It is categorised as a Execute tool in the Mcp Ap2 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for evaluate_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.
evaluate_order is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the evaluate_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 evaluate_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.
evaluate_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.