MCP: Earnie in your coding agent

Earnie is there when AI is looking for guidance.

Your agent pulls in packages, snippets and model files faster than anyone can review them. Point Claude, Cursor or your local model at Earnie's MCP and it asks before it commits. "Does this package have known vulnerabilities?" "Where did this snippet actually come from?" "What crypto does this library ship?" "What's inside this model file?" Licences too, but that's the easy part.

Grounded, deterministic answers from hard data. Policy checks run in-context, at the moment of adoption, not three sprints later in a scan report.

Works with

Merge-time checks: GitHub and GitLab

The gate that documents itself.

Every pull request checked against project policy. Pass, warn, or block, and every decision lands in the record.

Earnie CLI

Free. Local. Fast.

Scan a directory, check a dependency, verify a snippet, from your terminal, before anyone else sees it. Detection is free.

earnie scan .
↳ 412 files. 12 components. 0 violations.

Pre-commit hooks

Catch it before it's committed.

Earnie fires from your pre-commit hook and flags the violation in your console, before the code leaves your machine.