Obtener estado de cuenta del usuario
AI agents call obtener_estado_cuenta to retrieve information from IOL MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves account state data (saldo, posiciones, movimientos) from a financial trading platform. While it is a Read operation with no side effects, it accesses sensitive financial information that could enable reconnaissance for account takeover, fraud, or unauthorized trading. The high severity reflects the sensitivity of the data accessed despite the non-destructive nature of the operation.
From the tool's definition Tool name 'obtener_estado_cuenta' and description 'Obtener estado de cuenta del usuario' indicate retrieval of account status/financial information without modification.
Attacks that exploit this kind of access
Obtener estado de cuenta del usuario. It is categorised as a Read tool in the IOL MCP Server MCP Server, which means it retrieves data without modifying state.
Register the IOL MCP Server MCP server in PolicyLayer and add a rule for obtener_estado_cuenta: 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 IOL MCP Server. Nothing to install.
obtener_estado_cuenta 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 obtener_estado_cuenta 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 obtener_estado_cuenta. 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.
obtener_estado_cuenta is provided by the IOL MCP Server MCP server (pgallar/iol-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 →