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 Ap2 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
check_watchlists retrieves and queries data from multiple watchlist sources (OFAC, UN, EU, HMT, Interpol, adverse-media). It has no side effects—it does not create, modify, delete data, execute commands, or commit financial obligations. While watchlist screening is a compliance-critical function in a payment authorization context, the tool itself is a pure read/lookup operation.
From the tool's definition Tool performs screening queries against watchlists and returns results (hits, list names, entry dates, risk levels). The description specifies 'returns' information without mentioning data modification, deletion, or financial transactions.
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 Ap2, 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 Ap2 MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ap2 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 Ap2. 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 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.