AI agents call onpe_summary 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 summarizes existing electoral data without side effects. It returns aggregated national statistics about the 2026 presidential election, which is a read-only operation. The low severity reflects minimal blast radius—misuse would at worst return inaccurate data summaries to an end user, with no capability to modify underlying data, execute code, or affect financial systems.
From the tool's definition Tool name 'onpe_summary' and description 'Resumen agregado nacional 2026 1V (totales + por partido)' indicate retrieval and aggregation of national electoral summary data (totals and by party).
Attacks that exploit this kind of access
Resumen agregado nacional 2026 1V (totales + por partido). 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_summary: 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_summary 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_summary 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_summary. 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_summary 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 →