All activity
Park Jin Hyukleft a comment
Hey PH! I'm Jin — solo dev behind Clouvel and now Project Shield. I built Clouvel to help devs design before coding (PRD-first workflow for AI coders). But I kept seeing the same thing: even well-designed projects ship with hardcoded API keys, open MCP configs, and prompt injection sitting in tool descriptions. The AI writes fast, but nobody grades the output. So I built Shield. One command, 2...
Project ShieldOne command to security-grade your MCP server
Your AI tools connect to MCP servers — but who checks if those servers are secure?
Project Shield is a CLI that grades your MCP setup in one command:
`npx project-shield scan .`
It catches prompt injection in tool descriptions, missing auth in MCP configs, leaked API keys (regex + entropy + context), and PII exposure.
You get an A–F security grade, fix-it guides for every finding, and a deploy lock on F grade.
No signup. No dashboard. Just run it.
Free (5 scans/month) · Pro for teams.
Project ShieldOne command to security-grade your MCP server
Park Jin Hyukleft a comment
Hey Product Hunt Most AI coding assistants will happily build whatever you ask, even when the plan is missing requirements, edge cases, or security basics. That usually ends in messy code and surprises later. I built Clouvel: an MCP server that adds an upfront review step with 8 “manager” roles (PM, CTO, QA, Security, etc.) so you get pushback before you write code. - No PRD? It blocks and asks...
Clouvel No PRD, no code. AI managers review your plan before coding
8 AI managers help you think from every angle before you code.
How it works:
- No PRD → Coding blocked
- Incomplete PRD → Warning shown
- Complete PRD → Start building
Free: PRD gate + 3 managers (PM, CTO, QA)
Pro $7.99/mo: All 8 managers + verification tools
Solo dev tool. Same spec = same output, every time.
Clouvel No PRD, no code. AI managers review your plan before coding