sipi.bot — Spend Firewall for AI Agents is answering right now. Last checked 11 min ago. It exposes 3 tools.
Pre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.
Today is the operative word: we check sipi.bot — Spend Firewall for AI Agents every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.
claude mcp add sipi-bot-spend-firewall --transport http https://sipi.bot/api/mcp
https://sipi.bot/api/mcp
[mcp_servers.sipi-bot-spend-firewall]
url = "https://sipi.bot/api/mcp"
{
"mcpServers": {
"sipi-bot-spend-firewall": {
"url": "https://sipi.bot/api/mcp"
}
}
}
{
"servers": {
"sipi-bot-spend-firewall": {
"type": "http",
"url": "https://sipi.bot/api/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
evaluate_spend
firewall_status
add_spend_rule
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://sipi.bot/api/mcp | streamable-http | answering | 313 ms | 11 min ago |
Git-native policy layer for AI agents: check_action verdicts against rules approved via PR.
Free pre-action policy checks and data cleaning for autonomous AI agents.
AI agent spending controls. Set limits, blocklists, and caps. Approve transactions from your phone.
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
Xendit payment APIs for AI agents. Payment links, payouts, balances, and transactions.
Check SQL against your Vericto rules before it runs: blocks destructive or risky statements.
Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
Pre-execution security for AI agents on Base: guard token/tx/address + per-agent spend firewall.
Answers built from our own checks of this server.