Search

Hadolint-grade Dockerfile audit — 19 checks: secrets, privileges, supply chain, hygiene.

Deterministic prompt-injection detection & sanitization for AI agents via x402 on Base.

AEGIS MCP server — exposes scan / findings / score / compliance / fix-suggestion tools to any Model Context Protocol agent (Claude Code, Cursor, Continue, Zed). Five registered tools: aegis_scan, aegis_findings, aegis_score, aegis_compliance, aegis_fix_su

SoterAI adds prompt injection, jailbreak, PII leakage, and unsafe output protection to AI workflows.

MCP proxy for schema compression, tool access control, SSRF protection, injection detection, rate limiting and audit logging

Summarize flows/talkers/protocols from a pcap text export

Native macOS network monitor: every app's traffic to every domain, plus AI agent oversight with per-agent allowlists and tool/MCP server attribution. Free, open source (GPL-3.0), no telemetry.

A firewall and flight recorder for AI tool calls. Proxies MCP traffic, records it, and enforces policy.

**GitHub Repo URL:** https://github.com/ashlrai/phantom-secrets

A cybersecurity-focused MCP server that integrates AI for autonomous red teaming, threat hunting, and incident response automation.

Local-first CLI that catches launch blockers in AI-built Next.js/Supabase/Stripe SaaS apps.

MCP Tool Poisoning Scanner — Defensive scanning + offensive pentest tooling for MCP servers. Maps to OWASP MCP Top 10.

Governance SDK for AI agents. Verify actions (ALLOW/CLAMP/DENY), attest provenance, bind intents. Free tier auto-provisions 1,000 calls/month. Pay-per-call via x402 USDC. MCP, LangChain, CrewAI, AutoGen, OpenAI compatible.

Analyze an ADS-B feed/CSV for anomalies: callsign spoofing, squawk 7500/7600/7700, and unusual loiter patterns.

Dependency-free static analyzer that audits LLM agent tool/function definitions (OpenAI, Anthropic, MCP) for excessive agency, code-execution & SSRF sinks, secret access, and data-exfiltration surface — mapped to the OWASP 2025 LLM Top-10. Runs in CI.

Embeddable AI action firewall for MCP servers and APIs with JSON policies, signed receipts, spend caps, and simulation mode

7h3 Protocol — signed, capability-scoped, receipted WebMCP tools. Deterministic authorization for browser agents.

Zero-dependency tool-integrity pin for MCP servers and agent skills: approve once, refuse what changed

Multi-framework threat intelligence MCP server — STRIDE, DREAD, LINDDUN, and PASTA analysis for AI coding agents

SecTrust - auditable, always-on, multi-model AI colleague platform: cross-process task registry + DAG orchestration + HITL approvals + sandbox + compliance scanning + long-term memory, exposed as a zero-dependency MCP server.