Totales por categoría y top merchants para un mes YYYY-MM.
AI agents call report.monthly to retrieve information from Mcp Finance without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and summarizes expense data (monthly totals and merchant rankings). It queries existing data without creating, modifying, or deleting records, making it a Read operation. The severity is low because viewing financial summaries has minimal blast radius—no funds are moved, no data is destroyed, and no external actions are triggered.
From the tool's definition Tool generates 'Totales por categoría y top merchants' (totals by category and top merchants) for a month—a read-only aggregation/reporting operation with no modification, deletion, or execution of external systems.
Attacks that exploit this kind of access
Totales por categoría y top merchants para un mes YYYY-MM. It is categorised as a Read tool in the Mcp Finance MCP Server, which means it retrieves data without modifying state.
Register the Mcp Finance MCP server in PolicyLayer and add a rule for report.monthly: 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 Mcp Finance. Nothing to install.
report.monthly 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 report.monthly 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 report.monthly. 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.
report.monthly is provided by the Mcp Finance MCP server (toothlesstarantula/mcp-finance). 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 →