
ThornGuard
Safer MCP launch with inspection and audit trails
What it does
ThornGuard sits in front of MCP traffic so you do not have to bolt auth and guardrails onto every client by hand. It gives you per-instance activation, request inspection, redaction, and audit logs without changing the upstream MCP server.
Does the same job
all alternatives →
- MSMCP-Shield – Detect security issues in MCP servers2025 · github.com · ▲134
I noticed the growing security concerns around MCP (https://news.ycombinator.com/item?id=43600192) and built an open source tool that can detect several patterns of tool poisoning attacks, exfiltration channels and cross-origin manipulations. MCP-Shield scans your installed servers (Cursor, Claude Desktop, etc.) and shows what each tool is trying to do at the instruction level, beyond just the API surface. It catches hidden instructions that try to read sensitive files, shadow other tools' behavior, or exfiltrate data. Example of what it detects: - Hidden instructions…

- WTWiretap – Transparent WireGuard proxy server without root2022 · github.com · ▲118
- TBTailGuard – Bridge your WireGuard router into Tailscale via a containerSep 2025 · github.com · ▲150
My elderly parents are behind a 5G connection in rural areas, and I help them manage their network from overseas. I found a reasonably priced 5G router that can do external antennas required for it to work, but the only reasonable ways to get access to it is either through OpenVPN or WireGuard, the latter of which is much more lightweight and preferred with the memory constraints of the device. The problem with WireGuard is that it requires handling key management oneself, and configuring the keys to every device you want to access it from. It also doesn't play nicely together with other…
- DGDiesel-guard – Lint Diesel migrations for unsafe PostgreSQL patternsDec 2025 · github.com · ▲18
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com


Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com


Launched alongside, March 2026
the whole month →

Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com


