MCP Server

sipi.bot — Spend Firewall for AI Agents

io.github.kindrat86/sipi-bot-spend-firewall
Payments & Fintech Security Public & reachable MCP 2026-07-28

What this MCP does

Applies policy rules to proposed purchases, returning approved, blocked, or flagged decisions, and manages spend rules and firewall status.

add_spend_rule
Add a rule to the authenticated API key's isolated workspace.
Input schema
{'type': 'object', 'required': ['rule_type', 'params'], 'properties': {'label': {'type': 'string'}, 'action': {'type': 'string'}, 'params': {'type': 'object'}, 'priority': {'type': 'integer'}, 'rule_type': {'type': 'string'}}}
evaluate_spend
Check whether an autonomous agent is allowed to make a purchase BEFORE spending. Returns APPROVED, BLOCKED, or FLAGGED.
Input schema
{'type': 'object', 'required': ['amount'], 'properties': {'amount': {'type': 'number'}, 'category': {'type': 'string'}, 'merchant': {'type': 'string'}, 'description': {'type': 'string'}}}
firewall_status
Get private firewall stats for the authenticated API key.
Input schema
{'type': 'object'}
Added
firewall_status
Sept. 17, 2026, 12:42 p.m.
Added
add_spend_rule
Sept. 17, 2026, 12:42 p.m.
Added
evaluate_spend
Sept. 17, 2026, 12:42 p.m.