Security

Production-grade Security Model Context Protocol (MCP) platform for static, dependency, secret, configuration, mobile, and live security audits.

Soul-driven AI agent with Second Brain memory, permission-hardened tools, token budgets, and multi-channel access. Runs 24/7 from CLI or Telegram.

Authorization for MCP servers: OAuth 2.1 resource server, roles/permissions policy, permission-gated tools (2026-07-28)

MCP browser server - fetch web pages using real Chrome/Edge/Brave browser. Handles authentication, SSO, CAPTCHAs, and anti-bot protection. Browser automation for AI assistants.

Turn the HTTP routes of your existing Node.js app (NestJS, Express, Fastify, Koa, Hono, AdonisJS) into MCP tools for AI agents, reusing your auth, validation and rate limits.

MCP server for LeadVal — submit finished AI-agent conversations for scoring, poll them to a terminal state, and ask mid-conversation whether this workspace already knows the person you are speaking to. Four tools over stdio for Claude Desktop, Cursor or y

Command-line compliance test kit + security audit for A2A (Agent2Agent) protocol endpoints. Validates agent cards, JSON-RPC conformance, auth, and SSRF/TLS/CORS. Emits JSON, JUnit, SARIF, badge, snapshot diff.

Your MCP server won't connect. Find out why in 10 seconds. Diagnoses every server in your Claude Desktop, Claude Code, Cursor, VS Code, Cline, Zed and Gemini CLI configs - local and remote: missing commands, placeholder API keys, stdout pollution, silent

MCP server for adversarial security research — 6-phase pipeline from profile to disclosure

Node.js/TypeScript MCP server for AWS Single Sign-On (SSO). Enables AI systems (LLMs) with tools to initiate SSO login (device auth flow), list accounts/roles, and securely execute AWS CLI commands using temporary credentials. Streamlines AI interaction w

npm audit for MCP servers — grade any MCP server A–F on auth, SSRF, static keys, and prompt-injection surface.

Give your AI agent a signed, verifiable identity in one line.

MCP server for Altirs — AI guardrails (content safety, PII, prompt injection, hallucination) as tools for Claude Code, Claude Desktop, Cursor, and any MCP client

Turn a Supabase app into a polished end-user MCP server.

Agent-first format and validator for persistent cartographic design systems.

Tenant and permission isolation for LLM agent tool calls: a principal context on AsyncLocalStorage, a guard that scopes every call and audits it, and a test kit that proves no tool escaped.

MCP server com o catalogo do IAM Scope: 4.640 roles e 30.865 permissoes de seis nuvens (Entra ID, Azure RBAC, AWS IAM, GCP IAM, Google Workspace, IBM Cloud), mais as 17.591 acoes do Azure para escrever custom roles, respondendo na sua maquina.

MCP Server for identity verification, enterprise check, vehicle query, OCR recognition and risk assessment in China.

Scan, score, and enforce security policies on MCP servers. Risk scoring (A-F), SARIF output, policy engine, drift detection, aguara integration, CI/CD gate.

Capability-bounded execution for autonomous agents on Cowl. Let an agent trade from a shielded portfolio without ever holding a private key.