Retrieve chargeback (contestacao) detail for a charge: reason code, acquirer deadline, dispute amount, evidence status.
AI agents call query_chargeback 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 is fundamentally a Read operation—it retrieves and queries chargeback information without modifying, creating, or destroying data. However, severity is elevated to 'medium' rather than 'low' because the tool accesses sensitive financial dispute details that could be misused if an agent queries chargebacks belonging to other parties without authorization, potentially exposing confidential payment information.
From the tool's definition Tool name 'query_chargeback' and description 'Retrieve chargeback detail' indicate a retrieval/query operation with no modification.
Documented attack patterns abuse exactly the kind of access query_chargeback 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 query_chargeback:
{
"version": "1",
"default": "deny",
"tools": {
"query_chargeback": {}
}
}query_chargeback 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.
Retrieve chargeback (contestacao) detail for a charge: reason code, acquirer deadline, dispute amount, evidence status. 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 query_chargeback: 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.
query_chargeback 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 query_chargeback 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 query_chargeback. 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.
query_chargeback 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.