Search

A simple, evidence-first Swagger/OpenAPI security workbench with a policy-bounded MCP server.

Pay-per-call security verification for wallets, contracts, agents and apps, in USDC over x402.

Secure, observable Java 21 MCP server for governed read-only AI access to IBM Db2.

Apache-2.0 security extension proposal for the Model Context Protocol (MCP). Object-level signing, freshness/replay protection, mTLS transport, delegated authorization, sidecar protection of ordinary MCP servers. Rust workspace; published security audits under docs/security/.

Curated, auto-updating list of tools, standards, and research for securing Model Context Protocol (MCP) servers.

Official SupraWall MCP (Model Context Protocol) Security Plugin. Enforces deterministic guardrails, least-privilege tool access, and PII interception for AI agents.

Security scanner for OpenClaw skills, MCP servers, and agent tools. Detects prompt injection · data exfiltration · supply chain attacks — in under 10 seconds.

Review what an AI agent release changed at runtime (files, network, MCP tools), gate the PR, and report findings in code scanning. For AI platform and security teams.

🛡️ Production-grade Model Context Protocol (MCP) Server for Autonomous AI Security Bug Hunting, Persistent Pentest Memory, Dynamic Checklists, Secret Redaction, and Exploit PoC Generation.

MCP server for OT (Operational Technology) security standards and frameworks

Install the secure-code security skills into a Claude Code project, and connect MCP servers (secure-code-mcp or any other).

Security gate and deterministic lockfile for Agentic Resource Discovery (ARD) catalogs. Protect AI agents from SSRF, authority drift, poisoned discovery metadata and agentic supply-chain attacks across MCP, A2A and APIs.

Supabase RLS and security check for AI-built apps on Vercel + Supabase (Lovable, Bolt, Cursor, Claude Code): tables without RLS, using (true) policies, service role keys in client code, unsigned Stripe webhooks. Runs locally. Advice, not a gate.

A deterministic execution firewall for MCP agents. Local-first, open source, no LLM judging the thing it's meant to secure, no cloud dependency, no telemetry leaving your machine. It sits between your MCP client (Claude Desktop, Claude Code, Cursor, etc.) and your real MCP servers. It approves or blocks each tool call using explicit rules.

MCP server for CheckVibe security scanning — run security audits from AI coding agents

MCP server for Microsoft Patch Tuesday security updates (MSRC Security Update Guide)

Stratos - Azure Security Assessment MCP Server - 32 Professional Security Tools (With Annotations & Tests)

Comprehensive security sanitization library for Model Context Protocol (MCP) servers with trusted security libraries

Secure Model Context Protocol (SMCP) v1 - Production-ready security framework for MCP implementations

AI agent security scanner — prompt injection detection, SQL injection, PII isolation, threat intel.