elberacasa/umbra
by Various
The trust score for AI-generated code. One command verifies what your coding agent shipped: security findings with file:line evidence, Docker-sandboxed build/boot checks, and claim
MCP
elberacasa/umbra
Added 16 Sept 2026
Overview
Command-line tool that verifies AI-generated code. It runs security checks with file:line evidence, performs Docker-sandboxed build and boot tests, and generates claim receipts to detect when agents falsely report passing tests.
Best for
Best for
Teams shipping AI-generated code who want independent verification
Use cases
- Verify security of AI-generated commits
- Check build and boot in a Docker sandbox
- Audit whether coding agent test claims are truthful
How to use
Install
npx umbra-scan # check — scans the directory you're standing in Tested with
Claude Code, Cursor, Windsurf
Notes
Command-line tool that verifies AI-generated code. It runs security checks with file:line evidence, performs Docker-sandboxed build and boot tests, and generates claim receipts to detect when agents falsely report passing tests.
0 stars on GitHub. Last updated 2026-08-05. Licensed MIT.
Use cases
- Verify security of AI-generated commits
- Check build and boot in a Docker sandbox
- Audit whether coding agent test claims are truthful
Pros
- Concrete file:line security findings
- Sandboxed verification isolates risks
- Catches false test claims
Cons
- Requires Docker for build/boot checks
- No stars or community adoption yet
- Focused on verification, not fixing issues
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Concrete file:line security findings
- Sandboxed verification isolates risks
- Catches false test claims
Cons
- Requires Docker for build/boot checks
- No stars or community adoption yet
- Focused on verification, not fixing issues
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
OpenHands
All Hands AI
Open-source autonomous coding agent platform. Spins up a sandboxed dev environment, ships PRs end to end.
AutoGen
Microsoft
Microsoft's framework for multi-agent conversations. Agents that talk to each other to solve hard problems.
GPT Engineer
Various
CLI platform to experiment with codegen. Precursor to: https://lovable.dev
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
