Runtime security & observability guard for AI agents — intercepts LLM calls and tool calls before execution.
MCP server exposing CerbereAG runtime security checks (prompt injection, PII redaction, tool authorization) to any MCP-compatible AI agent (Claude, Cursor, Cline, custom agents).
Anthropic, PBC
Visionary sponsor
Bloomberg
Visionary sponsor
Hudson River Trading
Visionary sponsor
Meta
Visionary sponsor
NVIDIA
Visionary sponsor
Microsoft
Sustainability sponsor
Depot
Continuous Integration
AWS
Cloud computing and Security Sponsor
Datadog
Monitoring
Fastly
CDN
Google
Download Analytics
Sentry
Error logging
StatusPage
Status page