55 tools. 37 can modify or destroy data without limits.
10 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (gastos_flow_delete_categoria, gastos_flow_delete_cuenta, gastos_flow_delete_deuda_cobrar) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (gastos_flow_activar_gasto_recurrente, gastos_flow_create_categoria, gastos_flow_create_cuenta) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
gastos_flow_delete_categoria:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
gastos_flow_activar_gasto_recurrente:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
gastos_flow_get_categoria:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Gastos Flow server exposes 10 destructive tools including gastos_flow_delete_categoria, gastos_flow_delete_cuenta, gastos_flow_delete_deuda_cobrar. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Gastos Flow server has 27 write tools including gastos_flow_activar_gasto_recurrente, gastos_flow_create_categoria, gastos_flow_create_cuenta. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.
55 tools across 3 categories: Destructive, Read, Write. 18 are read-only. 37 can modify, create, or delete data.
One line change. Instead of running the Gastos Flow server directly, prefix it with Intercept: intercept -c gastos-flow.yaml -- npx -y @gastos-flow-mcp-server. Download a pre-built policy from policylayer.com/policies/gastos-flow and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.