AI agents call onpe_top_candidato_geo 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 appears to retrieve or query electoral candidate data filtered by geographic location, which is a Read operation with no side effects. The server's stated purpose is querying existing electoral data, not modifying it. Blast radius is minimal—misuse would only expose publicly available election data.
From the tool's definition Tool name 'onpe_top_candidato_geo' suggests querying top candidates by geographic region. Server description indicates it enables 'queries about the 2026 presidential election' and provides 'regional statistics.' The sibling tools (db_query, db_search,…
Attacks that exploit this kind of access
onpe_top_candidato_geo. 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_top_candidato_geo: 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_top_candidato_geo 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_top_candidato_geo 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_top_candidato_geo. 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_top_candidato_geo 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 →