Verify an EBANX webhook notification HMAC signature against the integration key. Local verification, no API call.
AI agents call verify_notification to retrieve information from Mcp Ap2 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
HMAC signature verification is a read-only security operation. It retrieves/validates data (the signature and integration key) to determine authenticity but produces no side effects—no state changes, financial commitments, or external operations. While part of a payment system (AP2), the tool itself only performs local verification, making it a Read operation with low severity.
From the tool's definition The tool performs 'local verification' of a webhook notification HMAC signature 'against the integration key' with 'no API call.' This is a cryptographic validation operation that reads and compares signatures without modifying state, creating obligations,…
Documented attack patterns abuse exactly the kind of access verify_notification 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 verify_notification:
{
"version": "1",
"default": "deny",
"tools": {
"verify_notification": {}
}
}verify_notification is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Verify an EBANX webhook notification HMAC signature against the integration key. Local verification, no API call. It is categorised as a Read tool in the Mcp Ap2 MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for verify_notification: 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.
verify_notification is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the verify_notification 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 verify_notification. 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.
verify_notification 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.