Security analysis, scanning and identity.
Local-first memory and coordination layer for AI coding agents. Shadow Brain stores source-backed project lessons, recalls them across Codex, Claude Code, Cursor, Cline, OpenCode, and other tools, generates resume briefings, audits memory quality, exports
CHIP + Atom of Thoughts (AoT) Agent Harness — multi-provider n8n community node with a Process Analyst Worker for operational case triage (email, document, automotive service). Pluggable vaults (Obsidian, Supabase) and Human-in-the-Loop gate.
Security evals for the AI era. Probes · Targets · Graders · Proof. Confirmed XSS / SQLi / BOLA / prompt-injection / MCP-RCE with reproducible proof attached to every finding.
Reusable Cloudflare remote-connector harness for MCP servers (auth-agnostic OAuth + streamable-HTTP McpAgent).
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix. For Claude Code, Cursor, Windsurf, Cline, OpenClaw.
Latten Installer — a Codex-ready MCP server that provisions, scans, and instruments TypeScript AI apps so cost, reach, and blast radius show up in Latten. Every change lands as a reviewable PR you approve.
Celo-first agent payment SDK: x402 + MPP settlement, ERC-8004 identity, and on-chain spending policy via the EnvoyFacilitator. Optional Solana, Stellar, Stripe, DEX/bridge, and unified-wallet modules via subpath imports.
Scaffold a production-ready Express 5 + TypeScript backend — pick a database + ORM (Postgres/SQLite/Drizzle or Mongo/Mongoose), auth (Auth0/JWT/Clerk), an optional Next.js front end, Sentry, an MCP server, and x402 payments, and get a project with only wh
7ots.com — your AI companion with a face of its own: a desktop pet that watches over your coding agent (Claude Code and shell hooks), a personal assistant (reminders, alerts, notes, opens sites, sees your screen if allowed) and a reproducible identity (fa
Security scanner for AI agent architectures - 220+ detection patterns and 5 runtime guard modules for prompt injection, SSRF, path traversal, credential exposure, MCP security, and OWASP ASI vulnerabilities
Guardrail plugin for OpenClaw that blocks prompt injection, jailbreak attempts, and sensitive credential exfiltration before agent dispatch.
Feature-rich MCP server for Black Duck Polaris — trigger SAST/SCA/DAST scans, query findings, generate reports (SBOM, SPDX, CycloneDX), manage policies, triage issues, and more. Works with Claude Code, Claude Desktop, GitHub Copilot, Cursor, and any MCP-c
MCP server for creating Vanisec one-time secrets. Encrypts locally; the server only ever receives ciphertext.
36 tools for AWS infrastructure, security compliance, AI workflows, and ACI governance.
TAPI v2 and legacy request signing plus rejection translation.
Let Claude Code log into websites and use your API keys without ever seeing them.
Wall data reader + self-hosted MCP server (single binary). Reads Wall export ZIPs and serves them locally for personal viewing, search, and LLM access.
Security scanner for MCP servers. Find vulnerabilities before your AI agent does.
Auto-generate AI-ready context from your codebase. One command → CONTEXT.md ready to paste into Claude, Cursor, ChatGPT or any MCP agent. Full MCP server mode included.
MCP SDK connector for BonkLM