A community-driven registry for the Claude Code ecosystem. Not affiliated with Anthropic.
22 packages found
A secure low code deception runtime framework, leveraging AI for System Virtualization.
Deterministic security proxy for MCP tool calls — iptables for MCP
Deterministic LLM prompt defense scanner — 12 attack vectors, pure regex, zero AI cost, < 5ms
Open-source cybersecurity analysis agent for Claude Code. Scans projects for vulnerabilities across all OWASP 2025 Top 1
Open-source permission control plane for AI agents. Scan, enforce, and audit every tool call.
Transparent MCP proxy with OpenTelemetry tracing. Wrap any MCP server and persist traces to SQLite, Postgres or MySQL.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development f
MCP server for reading and editing Word (.docx) documents with track changes, comments, footnotes, and structural valida
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more fra
AI Agent Security Middleware — 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + MCP
MCP server for AIR Blackbox. Expose audit, replay, scan, and compliance tools to any MCP-compatible agent or IDE.
The first quantum-inspired keyring built specifically for AI coding agents. Secure secrets with superposition, entanglem
Configuration governance for Claude Code. Bootstrap, audit, sync, and evolve .claude/ across projects.
AI-powered cybersecurity code review skill for Claude Code. 8 specialist agents, OWASP 2025, CWE Top 25, MITRE ATT&CK, 1
Eleven Claude Code skills ported to OpenCode: code-review, security-review, feature-dev, frontend-design + 7 more. One c
Open, audit-grade agentic data quality framework with portable industry packs
Local-first production-readiness system for AI-built apps: read-only audit, evidence-based 0-100 score, guided fixes, le
Cross-repo code knowledge graph for Java/Kotlin/JS/TS — MCP server, taint analysis, call graph, OWASP reports. 95% fewer
Security infrastructure your AI can't be — deterministic, daily CVE intel past your model's training cutoff, whole-repo-
MISP (Malware Information Sharing Platform) MCP server with built-in prompt injection defense via prompt-defense-audit
Security scanner for MCP servers - detect backdoors, exfiltration, and prompt injection
AI-powered code review CLI with multiple providers (Gemini, Claude, OpenAI). Features 95%+ token reduction via semantic