Secure sandboxed code execution with language-specific interpreters for Claude Desktop via E2B, featuring multi-language support and easy integration.

Natural-language control for Auth0 resources with configurable tool access, secure device authentication, and scoped permissions that emphasize least privilege.

Doris-oriented backend service with token-bound DB config, real-time validation, hot reload, multi-worker scaling, and secure token management.

MySQL database integration in Python with configurable access controls and schema inspection

Secure bridge enabling AI agents to fetch 2FA codes and passwords via Authenticator App with token-based access.

Fast, local code scanning with AI-assisted prompts and editor integrations to apply Semgrep rules during development.

Secure, containerized tool orchestration with policy enforcement, observability, and self-hosted governance for AI workflows.

A high-level framework for building MCP servers in TypeScript

Interact with Home Assistant including viewing and controlling lights, switches, sensors, and all other Home Assistant entities.

Bridges AI assistants with Aqara devices via the Model Context Protocol, enabling natural-language control, scenes, and automation across multiple homes with secure authentication.

AI-friendly code packaging with token accounting, security checks, and remote packing—distinctive for advanced AI workflows.

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration.

Automates vulnerability fixes from SAST results and integrates as a vendor-agnostic MCP server for AI-assisted code remediation.

Self-hosted, fast microVM sandbox platform with embedded sandboxes, agent-ready workflows, and OCI compatibility.

Real-time malware detection and policy-driven security across multiple ecosystems with AI-assisted vetting.

HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.

Deprecated integration enabling multi-language security scanning via stdio or streaming transport with Semgrep rules.

Adaptive deception runtime with LLM-powered decoys across multiple protocols, enabling prompt-injection detection and rich threat intel collection.

Secure, containerized MCP deployment with policy-driven access, registry, and observability for self-hosted, on-prem and cloud environments.

Universal MCP memory service providing semantic memory search, persistent storage, and autonomous memory consolidation for AI assistants across 13+ AI applications.

Unified, self-hosted MCP gateway with centralized discovery, access control, and observability for multi-server deployments.

A high-performance Model Context Protocol (MCP) server for Trino implemented in Go.

Comprehensive AI red-teaming suite with OpenClaw, MCP scans, and jailbreak testing for enterprise infra.

Call MCPs via TypeScript, masquerading as simple TypeScript API. Or package them as cli.