Manually resolve a charge as paid. Used for out-of-band settlement (e.g. underpayment you accept, delayed confirmation you want to honour).
AI agents use resolve_charge to commit financial operations through Mcp Afip — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly alters the financial status of a charge, marking it as paid without actual payment being processed through normal channels. In the context of AFIP (Argentine tax authority) and electronic invoicing, misuse could result in fraudulent settlement of tax obligations or invoices, constituting a financial operation with irreversible fiscal and legal consequences.
From the tool's definition 'Manually resolve a charge as paid' and 'out-of-band settlement (e.g. underpayment you accept, delayed confirmation you want to honour)'
Documented attack patterns abuse exactly the kind of access resolve_charge gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Afip, and nothing reaches the server without passing your rules. This is the rule we recommend for resolve_charge:
{
"version": "1",
"default": "deny",
"tools": {
"resolve_charge": {
"deny_if": [
{
"conditions": [],
"on_deny": "Requires human approval."
}
]
}
}
} Any call to resolve_charge is blocked until a human approves it. The rest of the server keeps working.
Free to start. No card required.
Manually resolve a charge as paid. Used for out-of-band settlement (e.g. underpayment you accept, delayed confirmation you want to honour). It is categorised as a Financial tool in the Mcp Afip MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Mcp Afip MCP server in PolicyLayer and add a rule for resolve_charge: 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 Afip. Nothing to install.
resolve_charge is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the resolve_charge 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 resolve_charge. 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.
resolve_charge is provided by the Mcp Afip MCP server (codespar/mcp-dev-latam). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Afip, 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 Afip tools catalogued and risk-classified — across an index of 43,000+ MCP servers.