AI agents call onpe_2021_chat 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 queries electoral data through conversational interaction. It performs read-only operations (retrieving mesa results, candidate votes, regional statistics) with no mutation, deletion, code execution, or financial impact. The conversational interface wraps underlying query operations without introducing side effects.
From the tool's definition Tool name 'onpe_2021_chat' and description 'Interfaz conversacional para elecciones presidenciales 2021' indicate a conversational interface for querying historical Peruvian electoral data.
Attacks that exploit this kind of access
Interfaz conversacional para elecciones presidenciales 2021 (1V/2V). 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_2021_chat: 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_2021_chat 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_2021_chat 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_2021_chat. 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_2021_chat 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 →