24 packages found
Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enfor
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 238 commands, 224 MC
Static pre-install security scanner for MCP (Model Context Protocol) servers — `npx mcpaudit <path>` flags command injec
rUvOS — the agentic operating system. A single static Rust binary that runs as an MCP server, giving Claude Code persist
Open-source runtime security and governance for AI agents, MCP tools, robotics, industrial automation, and physical AI.
Audit npm packages for security, maintenance, licenses and dependencies. Recommends install or write-from-scratch.
AI code security scanner MCP server — detects invisible Unicode, Trojan Source, homoglyphs, Glassworm steganography, rul
AI antivirus for developer agents: protect Codex, Claude Code, Cursor, Gemini, OpenCode, plugins, skills, MCP servers, a
Security, cost, and health governance proxy for MCP infrastructure — YAML policy engine, OAuth 2.1/OIDC, web dashboard,
🛡️ Modern Python code obfuscator - Enterprise-grade protection at 50% lower cost than PyArmor
RamiBot v3.8.0 is a local-first AI security operations platform integrating multi-LLM support, a dynamic red/blue team s
🤖 AI code quality gate for AI-generated code. Detects hallucinated packages, phantom dependencies, stale APIs, and more
Open-source permission control plane for AI agents. Scan, enforce, and audit every tool call.
Deterministic LLM prompt defense scanner — 12 attack vectors, pure regex, zero AI cost, < 5ms
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
Open source local-first PR scanner that finds dead code, security bugs, secrets, quality regressions, and AI-code mistak
MCP security trust layer. Scan packages, get trust verdicts, check incident exposure, query abuse database. 5 tools, no
Security infrastructure your AI can't be — deterministic, daily CVE intel past your model's training cutoff, whole-repo-
Security scanner for MCP servers - detect backdoors, exfiltration, and prompt injection
MCE (MCP Code Execution) is a production-grade MCP server that transforms Swagger/OpenAPI specs into LLM-native Python f
MCP server for AI agent governance - quantum-safe audit trails, policy enforcement, threat detection. Works with Claude
APIMesh — 23 pay-per-call web analysis APIs + 16-tool MCP server with autonomous API generation. Security audits, SEO, t
Open, audit-grade agentic data quality framework with portable industry packs