"Firewalla" matching MCP connectors:

Advisory policy preflight for AI-agent spend requests; never executes payments or accesses wallets.

EU AI Act Art-14 runtime oversight: allow / flag / gate-to-human on an agent action, with receipt.

Fail-closed action authorization, MCP risk scanning, x402 checks, and signed receipts.

Permission before writes. Gravity→DENYs→Session $0.25. Pilot $100; Gateway $299. Probe free.

The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...

sipi.bot — Spend Firewall for AI Agents

io.github.kindrat86

Pre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.

Real-time prompt injection and jailbreak detection for AI agents. Blocks instruction overrides, data exfiltration, tool poisoning and 8 attack types. Now with shared learning brain - confirmed attacks shared across the EMA network instantly. Grade A security for any AI pipeline.