Run a verification check on an applicant. A check is a bundle of one or more reports (document, facial_similarity_photo, watchlist, etc). This is the step that actually triggers the verification.
AI agents invoke create_check 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.
The tool executes an external verification workflow (KYC/AML checks) against third-party services. It is not a simple write/read — it actively triggers external operations whose effects depend on arguments (which report types are bundled). Given the AP2 payment protocol context, misuse could trigger spurious identity checks or watchlist screenings on individuals, making it high severity.
From the tool's definition 'triggers the verification' and 'Run a verification check on an applicant' — this initiates an external verification process with real-world consequences
Documented attack patterns abuse exactly the kind of access create_check 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 create_check:
{
"version": "1",
"default": "deny",
"tools": {
"create_check": {
"limits": [
{
"counter": "create_check_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}create_check 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.
Run a verification check on an applicant. A check is a bundle of one or more reports (document, facial_similarity_photo, watchlist, etc). This is the step that actually triggers the verification. 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 create_check: 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.
create_check 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 create_check 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 create_check. 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.
create_check 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.