Search

AI-powered Solana smart contract security audit server with 40 vulnerability patterns and 12 MCP tools covering access control, CPI safety, PDA, tokens, arithmetic, and DeFi exploits.

The Security & Cost Control Layer for AI Agents — Guard, Shield, and Sentinel tiers: budget control, per-agent credential isolation, OAuth scope enforcement, MCP policy enforcement, and compliance reporting.

The security standard for MCP and AI agents. 141 detection patterns, CORTEX threat intelligence, pre-deployment audit, intent firewall, flight recorder, and 390+ exports. Zero dependencies, runs locally.

Agent security scanner + runtime guard — 150 static patterns (23 categories), 26 runtime checks (5 layers), 0.016ms/scan, before_tool_call hook, CLI, SARIF. OpenClaw-compatible plugin.

The runtime security layer for AI agent commerce. Drop-in CLI + MCP server — blocks hallucinated purchases and keeps card credentials out of agent context. it only takes 0.1% of Hallucination to drain 100% of your wallet.

A neural network-powered security middleware and reverse proxy for the Model Context Protocol (MCP). Detects tool poisoning, shadowing, and prompt injection attacks using deep learning classifiers trained on SentenceTransformer embeddings.

MCP server that provides consistent service-build standards: TA/AA/DA architecture templates, fixed security baselines, selectable UI/UX design presets, and hardened container (Docker/Podman) guidelines.

Security scanner for AI-generated apps (React, Next.js, Vite, Lovable, Python, Cursor). Catches hardcoded secrets, hallucinated imports, copy-paste artifacts, accessibility issues, and vulnerabilities that traditional linters miss.

Supply-chain security audit for npm packages, as an MCP tool and a pay-per-call x402 endpoint. Detects typosquatting, malicious install scripts, token/credential exfiltration and other red flags BEFORE you run npm install.

Secure-by-default FastAPI->MCP bridge. Deny-by-default exposure, scope->tool auth that fails closed (even on STDIO), built-in rate limiting, PII redaction at the source, and a structured audit log — in-process, no gateway.

An MCP server that gives AI coding agents (Claude Code, Codex, Cline) safe, structured network & security reconnaissance tools — DNS, WHOIS, TLS, HTTP headers, and port scanning. For authorized testing and education only.

Local codebase intelligence for AI coding agents: structural repo map, change-safety gates, MCP security receipts, and tamper-evident ChangeEvidence packets. 100% local, zero API keys, zero network egress.

Secure identity infrastructure for AI agents — gives agents their own @agentlair.dev email address, encrypted credential vault, and cryptographically signed audit trail. Remote MCP server, no SMTP/DNS setup. npm: `@agentlair/mcp`.

Official Model Context Protocol (MCP) server for SPHIOR CODE — surface security findings from your GitHub repos directly into Cursor, Claude Code, VS Code, Cline, Continue, Windsurf, Zed and any MCP-compatible AI coding assistant.

Context-aware security scanner for AI agent skills, MCP servers, and tool configs. 95+ rules with false-positive reduction. Detects prompt injection, credential leaks, CORS misconfig, SSRF, tool poisoning, and data exfiltration.

** HTTP/API testing MCP server — make any HTTP request with custom headers/auth, check multiple endpoint health, decode JWT tokens, parse/build URLs, analyze security headers (HSTS, CSP, CORS, cookies).

A production-ready Model Context Protocol (MCP) server for CyberArk Privilege Cloud integration. Enables AI assistants and MCP clients to securely interact with privileged account management, safe operations, and platform configurations through 8 comprehensive tools.

Secure CLI tool that translates natural language to shell commands using local AI models via Ollama, with project memory system, reusable command templates (hooks), MCP (Model Context Protocol) support, and dangerous command detection

Static security + correctness audit for MCP server repos. Ships four checks. v0.5 fixes a v0.4 false-positive family where list-concatenation (e.g. `["kubectl"] + args + ["get"]`) was misclassified as string-interpolation in command_injection.

A comprehensive Model Context Protocol (MCP) server that provides web performance auditing, accessibility testing, SEO analysis, security assessment, and Core Web Vitals monitoring using Google Lighthouse. Enables LLMs and AI agents to perform detailed we