AI agents call onpe_list_foreign_geo 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 and enumerates electoral geography metadata (continents, countries, cities with foreign voting) from the ONPE database. It performs a query with no side effects, matches the 'list' pattern characteristic of Read operations, and poses minimal risk if misused by an AI agent—it simply returns informational data about voting locations.
From the tool's definition Tool name 'onpe_list_foreign_geo' and description 'Lista continentes/países/ciudades con voto extranjero' indicate a list/retrieval operation returning geographical data about foreign voting locations.
Attacks that exploit this kind of access
Lista continentes/países/ciudades con voto extranjero (foreign_catalog). 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_foreign_geo: 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_foreign_geo 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_foreign_geo 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_foreign_geo. 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_foreign_geo 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 →