AI agents call onpe_comparacion_mesa_cross_year 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 queries and retrieves electoral comparison data across years for a specific voting location (mesa). It performs no modifications, deletions, code execution, or financial transactions. The operation is read-only analysis of existing electoral statistics. Severity is low because unauthorized access to public electoral data poses minimal risk of harm.
From the tool's definition Tool name 'onpe_comparacion_mesa_cross_year' and description 'Compara una mesa entre dos años distintos' (Compares a mesa between two distinct years) indicate a comparison/query operation.
Attacks that exploit this kind of access
Compara una mesa entre dos años distintos (ej. 2021 vs 2026). 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_comparacion_mesa_cross_year: 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_comparacion_mesa_cross_year 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_comparacion_mesa_cross_year 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_comparacion_mesa_cross_year. 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_comparacion_mesa_cross_year 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 →