List outbound Pix payments with optional filters. Useful for reconciliation and agent-driven audit.
AI agents call list_pix_payments 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.
This tool retrieves and queries payment data without creating, modifying, deleting, or executing financial transactions. However, Pix is a real Brazilian payment system, and listing payment records could expose sensitive financial transaction history. The 'medium' severity reflects that while the tool itself is read-only, unauthorized access to payment records poses a moderate confidentiality risk.
From the tool's definition Tool name contains 'list' and description states 'List outbound Pix payments with optional filters' — a retrieval operation. Description explicitly mentions 'reconciliation and agent-driven audit', which are Read-category use cases with no modification.
Documented attack patterns abuse exactly the kind of access list_pix_payments 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 list_pix_payments:
{
"version": "1",
"default": "deny",
"tools": {
"list_pix_payments": {}
}
} list_pix_payments 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.
List outbound Pix payments with optional filters. Useful for reconciliation and agent-driven audit. 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 list_pix_payments: 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.
list_pix_payments 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 list_pix_payments 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 list_pix_payments. 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.
list_pix_payments 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.