Le catalogue réel des outils pour IA

Free spend guardrails for AI agents: approve/deny/ask_user, caps, dupes.

Deterministic preflight checks for credentials, fund transfers, writes, and prompt overrides.

Merge gates and safety checks for AI coding agents via MCP.

Advisory detectors for rumination, hyperfocus, and sycophancy. Never silently blocks.

Cloudflare Workers MCP server: ai-guardrails

Action-level governance for AI agents -- control what they DO, not what they SAY

An MCP server that provides Javelin Standalone Guardrails

Constitutional guardrails and loop detection for AI agents

AI Agent Guardrails MCP server - security layer

Pre-flight query cost and result-size guardrails for AI agents on BigQuery, Snowflake, Databricks

Guardrailed FHIR access for AI agents: PHI redaction, audit trail, step-up auth, tenant isolation

Local-first architecture guardrails and project context for JS/TS AI coding agents.

Enterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.

Keyless hosted MCP: pre-signature x402 payment verdict (GO/HOLD/STOP) with a signed receipt.

Policy review and purchase discovery for AI-agent commerce actions.

Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.

Pre-purchase trust, pricing and budget decisions for AI agents buying APIs and MCP tools.

Hard spend cap, OS sandbox, and signed receipts for unattended coding agents like Claude Code.

Zenable cleans up sloppy AI code and prevents vulnerabilities with deterministic guardrails

Access Oi Contexts, Workflows, Skills, Guardrails, Connections, and reporting tools.