[FacturaHub] Tax summary for declarations — VAT/IVA collected, income totals, expense deductions
AI agents call get_tax_summary to retrieve information from FacturaHub MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves aggregated tax and financial summary information for reporting purposes. It performs no modifications, deletions, or financial transactions—it merely reads and summarizes existing data. No side effects or irreversible actions are possible.
From the tool's definition Tool name is 'get_tax_summary' and description states it retrieves 'Tax summary for declarations — VAT/IVA collected, income totals, expense deductions'.
Attacks that exploit this kind of access
[FacturaHub] Tax summary for declarations — VAT/IVA collected, income totals, expense deductions. It is categorised as a Read tool in the FacturaHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the FacturaHub MCP Server MCP server in PolicyLayer and add a rule for get_tax_summary: 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 FacturaHub MCP Server. Nothing to install.
get_tax_summary 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 get_tax_summary 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 get_tax_summary. 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.
get_tax_summary is provided by the FacturaHub MCP Server MCP server (santy1422/facturahub-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 →