#ai-security

ToolHive - making MCP servers easy and secure

stacklok

ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.

ToolHive - making MCP servers easy and secure

StacklokLabs

ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.

Agentic Radar

splx-ai

A security scanner for your LLM agentic workflows

Compliant Llm

fiddlecube

Build Secure and Compliant AI agents and MCP Servers. YC W23

Agent Immune

denial-web

Adaptive security toolkit for AI agents. Assess inputs for prompt injection, scan outputs for credential/PII leaks, teach new attack patterns to semantic memory, harden prompts with role-lock and sandboxing, and monitor metrics — all locally via MCP. Zero false positives on bench

GuardVibe — Security MCP for Vibe Coding

goklab

Security MCP server with 300+ rules for AI-generated code. Scans Next.js, Supabase, Clerk, Stripe, Prisma, Hono, GraphQL, and 20+ modules. Zero config, runs locally.

Security scanning for Claude Code, Cursor, Windsurf. Detects secrets, scans MCP configs, generates threat models.

Zentric Protocol

ZentricProtocol

Prompt injection and PII detection MCP server for AI agents. Deterministic, sub-25ms. Returns CLEARED/ANONYMIZED/BLOCKED verdict with matched signatures, PII entities, and GDPR Art.30 audit report. 2,000 free requests/month.

Baidu Cloud LLM Security MCP Server focuses on addressing security issues such as compliance with generative content for third-party big models, internal security improvements for big models, and risk convergence for normalized big model operations