Fetch identity data (legal name, document, address) for an item. Pluggy endpoint: GET /identity?itemId=...
AI agents call list_identities 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 performs a read-only retrieval operation via GET request, which places it in the Read category. While there are no side effects or modifications, the sensitivity of the data being accessed (legal/personal identity information, documents, addresses) in the context of a payment protocol system elevates severity to 'high' due to potential privacy breach impact if misused by an AI agent.
From the tool's definition Tool description states 'Fetch identity data' and uses GET endpoint, indicating retrieval with no side effects. However, the data retrieved (legal name, document, address) is highly sensitive personal information.
Documented attack patterns abuse exactly the kind of access list_identities 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 list_identities:
{
"version": "1",
"default": "deny",
"tools": {
"list_identities": {}
}
}list_identities 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.
Fetch identity data (legal name, document, address) for an item. Pluggy endpoint: GET /identity?itemId=. 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 list_identities: 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.
list_identities 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 list_identities 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 list_identities. 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.
list_identities 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.