AI agents call onpe_filter_mesas 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 filters electoral voting table data based on vote predicates. It performs a search/query operation with no side effects, consistent with the 'Read' category. The inverse search functionality still returns results without altering data. Low severity because misuse would only surface incorrect election data, not cause system damage or enable harmful actions.
From the tool's definition Tool name 'onpe_filter_mesas' and description 'Búsqueda inversa de mesas por predicado de votos' (inverse search of voting tables by vote predicate) indicates a query/filter operation.
Attacks that exploit this kind of access
Búsqueda inversa de mesas por predicado de votos (azúcar sobre onpe_query). 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_filter_mesas: 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_filter_mesas 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_filter_mesas 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_filter_mesas. 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_filter_mesas 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 →