Retrieve the facial similarity result (selfie vs document photo). Returns match decision plus confidence score. Requires a completed workflow that included a similarity/selfie capability.
AI agents call retrieve_similarity_score to retrieve information from Mcp Afip without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves pre-computed biometric comparison results (facial similarity scores) from a completed workflow. It performs a read-only query operation that fetches existing data without creating, modifying, deleting, or executing external operations. While the underlying data is sensitive (biometric information), the tool itself only reads and returns results, making it a Read category risk.
From the tool's definition Tool description states 'Retrieve the facial similarity result' and 'Returns match decision plus confidence score.' The verb 'Retrieve' and 'Returns' indicate data retrieval without modification. No side effects or state changes are mentioned.
Documented attack patterns abuse exactly the kind of access retrieve_similarity_score gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Afip, and nothing reaches the server without passing your rules. This is the rule we recommend for retrieve_similarity_score:
{
"version": "1",
"default": "deny",
"tools": {
"retrieve_similarity_score": {}
}
}retrieve_similarity_score 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.
Retrieve the facial similarity result (selfie vs document photo). Returns match decision plus confidence score. Requires a completed workflow that included a similarity/selfie capability. It is categorised as a Read tool in the Mcp Afip MCP Server, which means it retrieves data without modifying state.
Register the Mcp Afip MCP server in PolicyLayer and add a rule for retrieve_similarity_score: 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 Afip. Nothing to install.
retrieve_similarity_score 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 retrieve_similarity_score 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 retrieve_similarity_score. 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.
retrieve_similarity_score is provided by the Mcp Afip MCP server (codespar/mcp-dev-latam). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Afip, 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 Afip tools catalogued and risk-classified — across an index of 43,000+ MCP servers.