Resolve a DICT key (CPF, CNPJ, email, phone, EVP) to the owner
AI agents call lookup_dict_key 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 is a straightforward read operation that resolves identifiers (CPF, CNPJ, email, phone, EVP) to associated account owners. It queries data without altering any state. While the AP2 server handles financial operations, this particular tool performs only a lookup, making it Read category with low severity—the blast radius of misuse is limited to information disclosure about key ownership.
From the tool's definition Tool description states it 'Resolve[s] a DICT key...to the owner' — a lookup operation that retrieves/queries data without modification. No mention of creating, modifying, deleting, or executing side effects.
Documented attack patterns abuse exactly the kind of access lookup_dict_key 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 lookup_dict_key:
{
"version": "1",
"default": "deny",
"tools": {
"lookup_dict_key": {}
}
}lookup_dict_key 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.
Resolve a DICT key (CPF, CNPJ, email, phone, EVP) to the owner. 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 lookup_dict_key: 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.
lookup_dict_key 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 lookup_dict_key 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 lookup_dict_key. 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.
lookup_dict_key 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.