Search

AI-powered security vulnerability scanner that runs locally via npm with zero infrastructure. Uses free HuggingFace models by default.

Local-first AI agent orchestrator with MCP server, secure file operations, shell execution, code indexing, and quality gates

A local security proxy MCP server for Neon's serverless Postgres API — default-deny, policy-enforced AI branch access.

67 DeFi security, wallet intelligence, and developer safety tools for AI agents. Powered by DeFi Shield via x402 micropayments.

Secure JWT and Base64 inspection Model Context Protocol (MCP) server. Decode and analyze tokens without exposing sensitive keys.

Zero-trust security proxy and runtime firewall for MCP agents. Intercepts JSON-RPC 2.0 over stdio between MCP clients and servers.

LLM security middleware: prompt-injection detection, PII protection, tool policy, cost tracking. Python port of ai-shield-core.

Warden — an open-source MCP gateway. A control plane for AI tool access: security screening and observability for Model Context Protocol servers.

Non-AI static analysis layer for AI IDEs and coding agents — bug detection, security scanning, and CVE checking via MCP

X-ray vision for npm packages — security scanner that audits source code, detects obfuscation, and flags supply chain risks before you install

AI-powered code security agent — MCP server for Cursor/Claude, mandatory pre-commit gate, and conversational PR/branch review

Argus — open-source security scanner with many eyes. SAST, DAST, SCA, Secrets, IaC, Terraform, Ansible via CLI and MCP.

Instant Shadow AI security audit for developer workstations. Discovers AI agents, scans MCP servers, local LLMs, and plaintext secrets.

Security-first, version-agnostic MCP gateway for Odoo 17/18/19 — works with stock and custom modules via YAML configuration

Forge production-ready MCP (Model Context Protocol) servers from databases or OpenAPI specs, with an optional ZTAI zero-trust security shield.

The security layer for AI agents — detect threats across 9 platforms with 316 rules, block them at runtime, guide remediation. Continuous protection.

Security copilot for your IDE. SAST, SCA, secrets, threat modeling — right where you code. Rust-native, zero config, runs 100% locally.

Make your AI coding agent dependency-security aware. Checks your project's dependencies against known CVEs so your agent can fix what it introduced — before merge.

Open-source security firewall for MCP (Model Context Protocol) servers. Scan, monitor, and enforce policies on AI agent tool calls.

A specialized MCP server providing AI models with comprehensive Chrome DevTools access through Playwright for autonomous debugging, performance analysis, and security inspection