AI agents call onpe_claim_verifier 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.
Given the server's primary purpose of querying electoral data and the naming pattern of sibling tools (all either query or export operations), this tool likely retrieves or verifies electoral claims against cached/live data without modifying records. The empty description reduces confidence slightly, but the lack of write/delete/execute keywords and consistency with read-only server operations suggests Read category.
From the tool's definition Tool name suggests verification/checking of claims, and context indicates ONPE server provides electoral data queries. No description provided, limiting certainty. Sibling tools (onpe_2021_chat, onpe_2021_comparacion_mesa, db_query) are read-only queries.
Attacks that exploit this kind of access
onpe_claim_verifier. 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_claim_verifier: 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_claim_verifier 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_claim_verifier 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_claim_verifier. 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_claim_verifier 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 →