buscar_manual
AI agents call buscar_manual 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.
This tool appears to search or retrieve information from healthcare manuals based on the naming convention 'buscar' (search) and server architecture focused on querying regulatory documents. No modification, deletion, execution, or financial operations are implied. While the description is empty (lowering confidence slightly), the sibling tools and server design strongly suggest Read category functionality.
From the tool's definition Tool name 'buscar_manual' combined with server context indicating semantic search and data retrieval from Brazilian healthcare manuals (SIH/SUS).
Attacks that exploit this kind of access
buscar_manual. 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_manual: 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_manual 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_manual 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_manual. 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_manual 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 →