38 packages found
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 238 commands, 224 MC
Transparent MCP proxy with OpenTelemetry tracing. Wrap any MCP server and persist traces to SQLite, Postgres or MySQL.
The approval and accountability layer for agentic AI. Identity → Policy → Approval → Trace. Try: npx sidclaw-mcp-guard d
Rust MCP server with 168 security tools for Claude — DNS/DNSSEC, TLS, email security, OSINT, threat intelligence, supply
Open source local-first PR scanner that finds dead code, security bugs, secrets, quality regressions, and AI-code mistak
The open-source execution engine for AI agents. 412 modules, MCP-native, triggers, queue, versioning, metering.
🛡️ Modern Python code obfuscator - Enterprise-grade protection at 50% lower cost than PyArmor
Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enfor
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more fra
Automated security investigation tool using Microsoft MCP Servers, GitHub Copilot, Python Modules and custom copilot-ins
🔬 Mobile runtime detection workbench for AI (iOS and Android)
[DEPRECATED] Moved to microsoft/agent-governance-toolkit
Cross-repo code knowledge graph for Java/Kotlin/JS/TS — MCP server, taint analysis, call graph, OWASP reports. 95% fewer
RamiBot v3.8.0 is a local-first AI security operations platform integrating multi-LLM support, a dynamic red/blue team s
Zaxy turns agent work into durable, auditable memory: a hash-chained Eventloom log as the source of truth, an embedded t
MCP server for AI agent governance - quantum-safe audit trails, policy enforcement, threat detection. Works with Claude
A secure low code deception runtime framework, leveraging AI for System Virtualization.
Connect Cursor, Copilot & Claude AI directly to Cheat Engine via MCP. Automate reverse engineering, pointer scanning, an
rUvOS — the agentic operating system. A single static Rust binary that runs as an MCP server, giving Claude Code persist
APIMesh — 23 pay-per-call web analysis APIs + 16-tool MCP server with autonomous API generation. Security audits, SEO, t
🚀 Ultimate Developer Productivity Suite - 11 specialized MCP servers for AI-powered code analysis, security scanning, b
A transparent Go proxy that intercepts, signs, and audits all MCP tool calls between any client and server, without modi
Passive recon tool. Zero credentials required. Finds Microsoft 365 & Google Workspace tenants, scores email security, fi
DockaShell is an MCP server that gives AI agents isolated Docker containers to work in. MCP tools for shell access, file
API security skills and rules for Cursor, Claude Code, Copilot, and all major AI coding agents. OWASP API Top 10 coverag
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
AI-first security scanner with 79 analyzers, 40,000+ detection rules, and repo poisoning detection for AI/ML, LLM agents
A curated, DevOps-focused list of Model Context Protocol (MCP) servers—covering source control, IaC, Kubernetes, CI/CD,
Agent Hub is an AI orchestration platform that transforms how developers and DevOps engineers interact with their toolch
Static pre-install security scanner for MCP (Model Context Protocol) servers — `npx mcpaudit <path>` flags command injec
MCP server combining Qdrant vector search, Neo4j knowledge graphs, and Crawl4AI web intelligence with agentic RAG capabi
Secure MCP server for safe, read-only DB access by AI agents, with SQL guardrails, table allowlists, PII masking, and au
Open, audit-grade agentic data quality framework with portable industry packs
MCP Server for Wazuh SIEM
MCP server for Thales CipherTrust RESTful Data Protection (CRDP)
A Pure-Java MCP Server for JaDX Android Reverse Engineering Tool
NOT for educational purposes: An MCP server for professional penetration testers including STDIO/HTTP/SSE support, nmap,
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.