Report the outcome of a chargeback dispute back to Legiti — i.e. whether the merchant won or lost the chargeback case after representation. Complements mark_order_fraudulent (which reports the chargeback itself). Disputes won are valuable counter-signal.
AI agents use mark_dispute_resolution to create or update resources in Mcp Afip — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Afip environment.
This tool updates dispute resolution records in a financial system (AFIP - Argentine tax authority). While it does not move money directly (Financial category), it writes/records outcomes that affect chargeback case status and merchant reputation signals ('counter-signal').
From the tool's definition Tool description states it 'Report[s] the outcome of a chargeback dispute back to Legiti' and references marking disputes with outcomes like 'merchant won or lost'. This modifies records of dispute resolution status.
Documented attack patterns abuse exactly the kind of access mark_dispute_resolution 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 mark_dispute_resolution:
{
"version": "1",
"default": "deny",
"tools": {
"mark_dispute_resolution": {
"limits": [
{
"counter": "mark_dispute_resolution_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mark_dispute_resolution stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Report the outcome of a chargeback dispute back to Legiti — i.e. whether the merchant won or lost the chargeback case after representation. Complements mark_order_fraudulent (which reports the chargeback itself). Disputes won are valuable counter-signal. It is categorised as a Write tool in the Mcp Afip MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Afip MCP server in PolicyLayer and add a rule for mark_dispute_resolution: 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.
mark_dispute_resolution is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the mark_dispute_resolution 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 mark_dispute_resolution. 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.
mark_dispute_resolution 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.