AI agents call onpe_list_departamentos to retrieve information from Onpe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query to list Peruvian administrative divisions and their constituent counts. It has no capacity to modify data, execute commands, delete information, or affect financial systems. The blast radius of misuse is minimal—returning incorrect electoral geography would have low impact. Categorized as Read with low severity.
From the tool's definition Tool name 'onpe_list_departamentos' and description 'Lista los 25 departamentos peruanos' indicate a listing/enumeration operation that retrieves static reference data (department names, province counts, district counts) with no modification or side effects.
Attacks that exploit this kind of access
Lista los 25 departamentos peruanos disponibles + #provincias y #distritos. It is categorised as a Read tool in the Onpe MCP Server, which means it retrieves data without modifying state.
Register the Onpe MCP server in PolicyLayer and add a rule for onpe_list_departamentos: 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 Onpe. Nothing to install.
onpe_list_departamentos 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 onpe_list_departamentos 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 onpe_list_departamentos. 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.
onpe_list_departamentos is provided by the Onpe MCP server (oscarzamora/onpe-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 →