Busca un item específico por nombre (búsqueda parcial, case-insensitive)
AI agents call buscar_item to retrieve information from MCP Inventario without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves data from the inventory without creating, modifying, deleting, or executing any operations. It is a simple search/query function typical of Read category tools. The low severity reflects minimal risk if misused—an agent searching inventory causes no side effects or data loss.
From the tool's definition Tool description states it 'Busca un item específico por nombre' (searches for a specific item by name) with case-insensitive partial matching. This is a read-only query operation with no modification or deletion capability.
Attacks that exploit this kind of access
Busca un item específico por nombre (búsqueda parcial, case-insensitive). It is categorised as a Read tool in the MCP Inventario MCP Server, which means it retrieves data without modifying state.
Register the MCP Inventario MCP server in PolicyLayer and add a rule for buscar_item: 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 Inventario. Nothing to install.
buscar_item 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_item 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_item. 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_item is provided by the MCP Inventario MCP server (olivio-git/mcp-experiment-inventory). 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 →