Busca todos los productos disponibles
AI agents call buscar_todos_productos to retrieve information from MCP Pedidos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves product data from the system without modifying, deleting, or executing any actions. It is a read-only retrieval operation that returns information about available products. There is minimal risk of misuse as the worst outcome would be information disclosure about the product catalog.
From the tool's definition Tool name 'buscar_todos_productos' (search all products) and description 'Busca todos los productos disponibles' (searches all available products) indicate a query/search operation with no side effects.
Attacks that exploit this kind of access
Busca todos los productos disponibles. It is categorised as a Read tool in the MCP Pedidos MCP Server, which means it retrieves data without modifying state.
Register the MCP Pedidos MCP server in PolicyLayer and add a rule for buscar_todos_productos: 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 Pedidos. Nothing to install.
buscar_todos_productos 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_todos_productos 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_todos_productos. 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_todos_productos is provided by the MCP Pedidos MCP server (reyesbho/mcp-moments). 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 →