23 packages found
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewritin
Local guardrails for AI coding agents. Wraps any MCP server and blocks destructive tool calls — DROP TABLE, rm -rf, forc
Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enfor
Open-source permission control plane for AI agents. Scan, enforce, and audit every tool call.
Veto MCP — gives every major AI CLI (Claude Code, Codex, Gemini, Cursor, Windsurf) a council of 49 specialist agents + 9
AI agent firewall that intercepts tool calls (file, shell, network) and enforces deterministic policies at sub-microseco
Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Olla
Reliability & security proxy for the Model Context Protocol (MCP). Self-healing connections, runtime tool-poisoning/shad
The most powerful Android RPA agent framework, next generation mobile automation.
Open-source security gateway for MCP agents and tools. Inspect tool calls before execution, enforce policy, block risky
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 238 commands, 224 MC
Active development continues at ScopeBlind/scopeblind-gateway. - Security gateway for MCP servers. Cedar policy engine,
The approval and accountability layer for agentic AI. Identity → Policy → Approval → Trace. Try: npx sidclaw-mcp-guard d
The open source circuit breaker for AI agents. Real-time security, secret DLP, and loop burn prevention for Claude Code,
NOT for educational purposes: An MCP server for professional penetration testers including STDIO/HTTP/SSE support, nmap,
safer-dependencies is a security layer for Claude Code that audits packages before they’re added to your project. It det
Teaches Claude to use a dozen visualization-building tools — raster, SVG, web, video, terminal, interactive, gaze plots,
Official companion repository for our survey "A Survey of the OpenClaw Ecosystem: From Platform Extensibility to Constra
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
Browser-automation agent for Chrome — natural-language tasks executed through native tool calling, scoped Skills, CDP ke
Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integratin
Local-first MCP server for AI visibility audits: GEO/AEO, AI SEO, llms.txt, schema, sitemap and AI crawler readiness.
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic fo