Le catalogue réel des outils pour IA

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

AI agents need permission before production SQL writes. Pilot $100 · Gateway $299. Lint≠authorize.

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

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

Structural similarity-based code filter. Stops malicious code pattern reaching execution tools.

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

Deterministic pre-execution safety certification for autonomous AI agents.

Budget, payment and audit controls for AI agent API calls and MCP tool calls.

Token guard and rate limiter preventing runaway API cost spikes for OpenAI and Anthropic.

Governed OPNsense + pfSense firewall ops: rules, NAT, VPN, DHCP, RCA. 35 tools.

Multi-agent LLM security layer detecting prompt injection and jailbreaks.

Three-layer firewall for MCP: content, egress and action policy. Proxy or server.

MCP security firewall: stdio wrap proxy or inspection tools; zero runtime dependencies.

Govern model, retrieval, memory, and tool access for AI applications and agents.

Inspect one endpoint's served certificate, expiry, hostname coverage, and accepted TLS versions.

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

Practice questions for the four Claude certifications. The assistant never sees the key.

French RNCP/RS certification registers: search, sheets, blocs, validity, SIRET habilitation.

Every NIST FIPS 140 certificate, plus the modules-in-process queue NIST publishes only as a page.

Intent execution engine for autonomous agent task routing