IDCheck: global sanctions / adverse-media screening. Covers OFAC (US Treasury), UN, EU, HMT (UK), Interpol Red Notices, and curated adverse-media sources. Pass cpf or name; returns hits with list name, entry date, and risk level.
AI agents call check_watchlists to retrieve information from Mcp Afip without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a compliance lookup operation similar to a database query. It accepts input (cpf or name) and returns structured results (hits, list names, dates, risk levels) without side effects. While compliance screening can inform financial decisions, the tool itself does not move money, execute code, or modify data.
From the tool's definition check_watchlists is a screening/querying tool that 'returns hits with list name, entry date, and risk level' — it retrieves and checks data against sanctions and adverse-media databases without modifying, executing, or destroying anything.
Documented attack patterns abuse exactly the kind of access check_watchlists 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 check_watchlists:
{
"version": "1",
"default": "deny",
"tools": {
"check_watchlists": {}
}
}check_watchlists 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.
IDCheck: global sanctions / adverse-media screening. Covers OFAC (US Treasury), UN, EU, HMT (UK), Interpol Red Notices, and curated adverse-media sources. Pass cpf or name; returns hits with list name, entry date, and risk level. It is categorised as a Read tool in the Mcp Afip MCP Server, which means it retrieves data without modifying state.
Register the Mcp Afip MCP server in PolicyLayer and add a rule for check_watchlists: 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.
check_watchlists 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 check_watchlists 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 check_watchlists. 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.
check_watchlists 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.