Search

No-code Claude Code hooks that forward raw lifecycle/tool events to a Radware LLM Protection ingest endpoint.

IP allowlist guard for MCP servers. Ships with OpenAI/ChatGPT egress IP ranges and supports custom CIDR ranges. Zero dependencies.

Model Context Protocol server for getdebug. Lets Claude, Cursor, and any MCP-compatible AI client read your projects, findings, and fixes.

Detection engine: regex + schema + semantic analysis for MCP tool definitions

Verified dependency audit as an MCP tool: a checked-against-the-installed-version verdict any AI agent can call, not a raw scan.

Policy-as-code enforcement for MCP tool calls

Trust scores for MCP servers.

VMOO数据库MCP服务器集合 - 支持开发和生产环境的安全数据库访问

Govern MCP, tool calls, and LLM traffic for AI agents — across LangGraph, Claude Agent SDK, and OpenAI Agents.

Trust-gated MCP middleware for FastMCP via Dominion Observatory

Check what Claude Code has been storing on your machine

AI governance platform — policy enforcement for AI-assisted development. Four enforcement layers (IDE, MCP, Git hooks, PR Gate), 739 detection rules, 18+ compliance frameworks.

VibeDefend — one-shot installer for CybeDefend's MCP server and Claude Code / Cursor / Codex / Windsurf hooks (for AI coding agents).

Model Context Protocol (MCP) server exposing Tenable.io via pyTenable

VibeCheck Ultimate CLI — Ship with confidence. 65+ commands merged from 4 codebases: kernel infrastructure, ISL verification, Reality Mode, Agent Firewall, MCP Server.

Database schemas and Drizzle ORM integration for RevealUI.

Self-hosted firewall for AI agents — a transparent MCP gateway that intercepts every tool call, applies an allow/deny/ask policy with human-in-the-loop approval, and streams an audit trail to your own control plane.

Trust badges for MCP tool calls - RFC-006 & RFC-007 implementation

SAFE Authorization Protocol for MCP tool calls — SAP/1.0 reference implementation

Prompt injection detection using behavioral analysis. Weak models as sensitive sensors.