perfil_auditoria
AI agents call perfil_auditoria to retrieve information from Manual RAG — SIH/SUS Query System without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The naming pattern and server context (RAG system for querying healthcare manuals and regulatory data) indicate this is a retrieval tool. No indication of write, delete, execute, or financial operations. The empty description reduces confidence, but the semantic pattern of sibling tools and the audit-related name suggest read-only profile retrieval functionality typical of this MCP server's purpose.
From the tool's definition Tool name 'perfil_auditoria' suggests retrieving audit profile information. The description is empty, limiting certainty.
Attacks that exploit this kind of access
perfil_auditoria. It is categorised as a Read tool in the Manual RAG — SIH/SUS Query System MCP Server, which means it retrieves data without modifying state.
Register the Manual RAG — SIH/SUS Query System MCP server in PolicyLayer and add a rule for perfil_auditoria: 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 Manual RAG — SIH/SUS Query System. Nothing to install.
perfil_auditoria 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 perfil_auditoria 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 perfil_auditoria. 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.
perfil_auditoria is provided by the Manual RAG — SIH/SUS Query System MCP server (leonardo-amaral-3/mcp-datasus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →