AI agents call onpe_lookup_ubigeo 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 retrieves geographic location information (UBIGEO codes) from the electoral database. Lookup and search operations are inherently read-only with no capability to modify, delete, or execute operations. The blast radius of misuse is minimal—an agent could only retrieve electoral geographic data that is already public or authorized for query access.
From the tool's definition Tool name 'onpe_lookup_ubigeo' indicates a lookup operation. UBIGEO is Peru's geographic coding system (código de ubicación geográfica). Lookup operations are queries for information retrieval without side effects.
Attacks that exploit this kind of access
onpe_lookup_ubigeo. 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_lookup_ubigeo: 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_lookup_ubigeo 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_lookup_ubigeo 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_lookup_ubigeo. 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_lookup_ubigeo 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 →