IDCheck: Politically Exposed Person screening. Pass cpf (preferred) or name; returns matches with role, jurisdiction, and source. A subject is PEP if they currently hold — or held in the last 5 years — a prominent public function per Bacen Circular 3,978/2020.
AI agents call check_pep 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.
The tool queries a politically exposed person (PEP) database and returns matching records. This is fundamentally a read operation—it retrieves and screens information without modifying data or executing financial actions. Severity is medium because misuse could facilitate fraud or regulatory evasion (e.g., bypassing sanctions checks), but the tool itself only reads/queries existing data.
From the tool's definition Tool performs screening/query operation: 'Pass cpf (preferred) or name; returns matches with role, jurisdiction, and source.' No modification, deletion, or financial transaction occurs. It retrieves and checks data against a PEP database.
Documented attack patterns abuse exactly the kind of access check_pep 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_pep:
{
"version": "1",
"default": "deny",
"tools": {
"check_pep": {}
}
}check_pep 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: Politically Exposed Person screening. Pass cpf (preferred) or name; returns matches with role, jurisdiction, and source. A subject is PEP if they currently hold — or held in the last 5 years — a prominent public function per Bacen Circular 3,978/2020. 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_pep: 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_pep 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_pep 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_pep. 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_pep 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.