Face authentication against a base image (typically the document photo). Returns match_score + liveness verdict + spoofing indicators. POST /v1/biometrics/face.
AI agents call face_authentication 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 reads/compares biometric data and returns authentication results. It does not create, modify, delete, or transfer anything. However, severity is medium because it handles sensitive biometric PII, and in a payment/agent protocol context, a spoofed or manipulated result could bypass authentication controls leading to financial or identity fraud.
From the tool's definition 'Face authentication against a base image... Returns match_score + liveness verdict + spoofing indicators' — it performs a verification/query operation and returns results without modifying data
Documented attack patterns abuse exactly the kind of access face_authentication 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 face_authentication:
{
"version": "1",
"default": "deny",
"tools": {
"face_authentication": {}
}
}face_authentication 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.
Face authentication against a base image (typically the document photo). Returns match_score + liveness verdict + spoofing indicators. POST /v1/biometrics/face. 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 face_authentication: 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.
face_authentication 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 face_authentication 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 face_authentication. 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.
face_authentication 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.