I work at the intersection of LLM reasoning, MCP tooling, and SOC automation — building the security layer agentic systems need before they're trusted with real infrastructure, and building agents that do SOC work directly.
🛡️ mcpscan
Supply-chain security scanner for MCP servers & Claude Code projects.
Problem: MCP servers ship with zero standard vetting — tool-poisoning, command injection, over-broad permissions, and leaked secrets go straight into .claude/ directories.
Stack: Python, zero runtime deps, SARIF 2.1.0 output for GitHub code scanning, CI-ready.
Status: active, CI-ready
🔎 vulnscan
AI-powered vulnerability intelligence scanner. Problem: dependency vulnerability lists are noisy — a CVE hit doesn't tell you what's actually exploitable in your usage. Stack: Python · OSV.dev lookups across 7 ecosystems (Python, Node, Go, Maven, Ruby, NuGet, Rust) · LLM-backed exploitability + remediation analysis. Status: active
🌐 BraveMCP
Local-first browser memory, accessible by Claude. Problem: Claude has no memory of what you've browsed — you re-explain context every session. Stack: TypeScript · browser extension + MCP server · fully local, no cloud sync. Status: shipped, v0.2.0
MCP server exposing defensive SecOps helpers: IOC extraction, defang/refang, hashing, password entropy, CIDR math, repo command-shadowing checks. Status: active
AI-powered SOC built entirely on Microsoft infrastructure — no Sentinel, no third-party SIEM. Problem: most SOC automation assumes a SIEM budget teams don't have. Stack: Copilot Studio · Power Automate · Microsoft Graph API · 5 coordinating agents (identity threat, phishing investigation, compliance/audit, SOC summary, orchestrator). Status: active
🧠 agent-memory-protocol (AMP)
Open protocol for AI agent memory interoperability — like MCP, but for memory. Problem: every agent framework reinvents memory storage; nothing shares across vendors or sessions. Stack: HTTP-native spec · Memory Cell schema · access control · decay-ranked semantic search · active→stale→archived lifecycle. Status: spec stage, pre-PyPI
Merged upstream:
| PR | Project | Change |
|---|---|---|
| #4125 | zalando/skipper | Isolated + applied 30s timeout to upgrade proxy dialer |
| #5817 | gpustack/gpustack | Propagated asyncio cancellation, removed mutable default args |
| #2725 | teamhanko/hanko | Refactored OAuth providers to propagate context, fixed duplicate defer |
| #40 | kerlenton/mcpsnoop | Added stdin-piped session support |
Also tracking the MCP ecosystem via awesome-mcp-servers.
| Repo | What it does |
|---|---|
| sentinelscout | Multi-source OSINT aggregator — VirusTotal, AlienVault OTX, Shodan, NVD, GitHub — with AI correlation |
| autoreview | AI-powered PR code review CLI, multi-LLM (OpenAI, DeepSeek, Claude, Ollama) |
| streamblind-poc | PoC + fix for asynchronous telemetry blindness & state desync in AI streaming clients |
| claude-token-monitor-usage | Local-first desktop HUD for Claude.ai / Claude Code quota and token-cost tracking |
| dev-to-mcp | MCP server for the dev.to API — browsing, challenge tracking, authenticated publishing |
| devto-challenge-agent | Multi-agent system for dev.to challenge research, writing, and performance tracking |
| nexora-second-brain | AI-powered second brain on Notion, Claude as the intelligence layer |
| Period | Repository | Context & Footprint | Stack |
|---|---|---|---|
| 2022 | BARELANG-MRT / B-MRT.github.io | Team site for a robotics competition entry (archived) | HTML |
| 2023 | Keamanan-Basis-Data | Database security coursework, published (archived) | — |
| 2024 | e_logbook | Logbook web app (archived) | PHP |
| 2025 | security-automation-notes | Scripts for repetitive security tasks — email analysis, log review, system checks | Shell |
| 2025 | cybersecurity-communication-guide | Interactive guide for explaining security concepts to non-technical audiences | TypeScript, React |
| 2025 | phising101-kiel | Phishing awareness reference material | JavaScript |
| 2025–26 | Freelance client builds — deddy-tour-travel-premier, malay-rental-batam, 4care_medicalcentre, magal-restaurant, stefan-music-learn | Client-commissioned sites (private) | Next.js / TypeScript |
| 2026 | ai-webinar-itdel | Presentation materials for an AI-in-industry webinar at Institut Teknologi Del | TypeScript |
| 2026 | personal-portfolio | Earlier Next.js personal site — superseded by the live Astro build at kielltampubolon.id (archived) | TypeScript |
| 2026 | devto-autopublish | Automated publishing pipeline for dev.to | JavaScript |
| 2026 | nebula-drift / solstice-game | Browser games, zero dependencies | JavaScript / HTML |
| 2026 | gmaps-extractor | Chrome extension for B2B lead extraction from Google Maps (private) | JavaScript |
| 2026 | automation-logan | HR clock-in/out automation bot, VPS + Cloudflare Workers deploy targets (private) | Python / JavaScript |
(Earlier school/web projects and one-off client sites not listed here remain visible in the full repository list.)