DepScope for Homebrew
Homebrew formulae intelligence — one API, every formula.
The problem
AI coding agents (Claude, Cursor, ChatGPT, Copilot) recommend Homebrew packages based on training data 6-12 months stale. Recent CVEs missed, deprecated libraries still suggested, package names sometimes hallucinated.
Every agent also queries formulae.brew.sh independently — billions of redundant fetches a day, tokens burned parsing JSON the model doesn't need.
One API call — live health, vulnerabilities, alternatives
curl https://depscope.dev/api/check/homebrew/git
Returns a health score, list of live CVEs, deprecation flags, latest version, alternatives — all from OSV + GitHub Advisory Database, cached.
For AI agents that prefer token-efficient responses:
curl https://depscope.dev/api/prompt/homebrew/git
Same signal, much more compact payload — less input tokens per decision.
Integrate in one line
Claude Desktop / Cursor MCP server on npm:
npm install -g depscope-mcp
GitHub Actions CI Audit your Homebrew dependencies on every PR:
- uses: cuttalo/depscope@main
with:
ecosystem: homebrewAny language Just call the API. No auth, 200 req/min.
Next steps
Package intelligence is infrastructure. DepScope is the shared layer so every AI coding agent — and every developer — can rely on the same live data. Open infrastructure, MIT, EU-hosted.