AI agents call onpe_audit_coverage 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 reports on electoral data coverage status—specifically identifying gaps or 'huecos' (holes) in vote data by department. It is a read-only audit function that queries or lists data without side effects, modifications, or irreversible actions. Consistent with the sibling tools (db_query, db_search, onpe_2021_export_*) which are all data retrieval operations.
From the tool's definition Tool name 'onpe_audit_coverage' and description 'Matriz de cobertura por departamento: mesas sin votos hidratados' indicate retrieval of audit/coverage data (matrix showing department coverage and unfilled voting tables).
Attacks that exploit this kind of access
Matriz de cobertura por departamento: mesas sin votos hidratados ('huecos'). 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_audit_coverage: 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_audit_coverage 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_audit_coverage 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_audit_coverage. 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_audit_coverage 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 →