Le catalogue réel des outils pour IA

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

MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.

Register every AI agent, log every action, prove it. EU AI Act compliance built in.

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

ARGUS-3 stdio MCP with WARDEN firewall: argus_ask, argus_status, argus_capabilities.

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

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

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.

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.

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

Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.

Verified context layer for AI coding agents — prunes, compresses, indexes, remembers. 32 MCP tools.

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

Zero-Trust MCP gateway securing internal database tools behind an API key firewall.

AI security firewall & DLP proxy protecting API keys and blocking destructive commands.

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

AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.