Procura clientes (endpoint de pesquisa, mais flexível que a listagem).
AI agents call procurar_clientes to retrieve information from MCP Officegest without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search/query operation on client records. It retrieves data without modifying anything. The description emphasizes it is a search endpoint, analogous to a flexible listing/filtering operation. No side effects are indicated.
From the tool's definition Procura clientes (endpoint de pesquisa, mais flexível que a listagem) — 'procurar' means 'search/find', and the description explicitly calls it a 'search endpoint'
Attacks that exploit this kind of access
Procura clientes (endpoint de pesquisa, mais flexível que a listagem). It is categorised as a Read tool in the MCP Officegest MCP Server, which means it retrieves data without modifying state.
Register the MCP Officegest MCP server in PolicyLayer and add a rule for procurar_clientes: 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 Officegest. Nothing to install.
procurar_clientes 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 procurar_clientes 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 procurar_clientes. 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.
procurar_clientes is provided by the MCP Officegest MCP server (rubencodex86/officegest-api-v2-mcp). 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 →