Credit + financial profile for a CPF/CNPJ — income, score, declared assets, banking, default history. POST /v1/datasets/persons.
AI agents call financial_data 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.
This tool queries and retrieves sensitive financial and personal data (credit scores, income, assets, banking history, defaults) without creating, modifying, or deleting records. While the data accessed is highly sensitive (justifying 'high' severity due to privacy/fraud risk if misused), the core operation is Read—extracting information. POST is used for filtering/querying, not creating resources.
From the tool's definition Tool retrieves 'Credit + financial profile for a CPF/CNPJ — income, score, declared assets, banking, default history' via POST /v1/datasets/persons. Despite POST method, the description indicates data retrieval with no modification or deletion mentioned.
Documented attack patterns abuse exactly the kind of access financial_data 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 financial_data:
{
"version": "1",
"default": "deny",
"tools": {
"financial_data": {}
}
} financial_data 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.
Credit + financial profile for a CPF/CNPJ — income, score, declared assets, banking, default history. POST /v1/datasets/persons. 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 financial_data: 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.
financial_data 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 financial_data 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 financial_data. 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.
financial_data 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.