Step 1 of 3DS2 — submit device-data-collection (DDC) output to Worldpay to determine whether a challenge is required. Returns either a frictionless result or a challenge lookup reference.
AI agents invoke lookup_3ds 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 payment authentication service (Worldpay) and triggers a 3DS2 lookup flow. It does not directly move money but initiates a step in a payment authorization chain, making it an Execute-level action. It is part of a financial flow but does not itself commit a financial obligation, so Execute is the most appropriate category.
From the tool's definition 'submit device-data-collection (DDC) output to Worldpay to determine whether a challenge is required' — triggers an external operation against Worldpay's 3DS2 authentication service
Documented attack patterns abuse exactly the kind of access lookup_3ds 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 lookup_3ds:
{
"version": "1",
"default": "deny",
"tools": {
"lookup_3ds": {
"limits": [
{
"counter": "lookup_3ds_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}lookup_3ds 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.
Step 1 of 3DS2 — submit device-data-collection (DDC) output to Worldpay to determine whether a challenge is required. Returns either a frictionless result or a challenge lookup reference. 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 lookup_3ds: 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.
lookup_3ds 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 lookup_3ds 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 lookup_3ds. 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.
lookup_3ds 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.