buscar_procedimento
AI agents call buscar_procedimento 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 ('buscar' = search in Portuguese) and the server's purpose as a query/retrieval system strongly suggest this is a read-only lookup tool for procedure information from Brazilian healthcare databases. No evidence of write, execute, destructive, or financial operations. Low severity: retrieving procedure data has minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'buscar_procedimento' (search/retrieve procedure) indicates a read operation. Description is empty, limiting confidence.
Attacks that exploit this kind of access
buscar_procedimento. 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 buscar_procedimento: 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.
buscar_procedimento 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 buscar_procedimento 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 buscar_procedimento. 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.
buscar_procedimento 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 →