AI agents call onpe_query 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 is explicitly designed for querying electoral data with filtering, sorting, and pagination. It retrieves and presents information without modification. The 'motor analítico' (analytical engine) framing confirms a read-only analysis purpose. Even with access to sensitive electoral data, the tool itself cannot alter, delete, or execute arbitrary operations—only retrieve structured query results.
From the tool's definition Tool description indicates 'select + where + order + paginación' — standard read-only SQL operations (SELECT, WHERE, ORDER BY, pagination). No CREATE, UPDATE, DELETE, or DROP operations mentioned.
Attacks that exploit this kind of access
Motor analítico estructurado (fase inicial): select + where + order + paginación. 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_query: 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_query 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_query 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_query. 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_query 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 →