Headless Code Editor MCP Server — security audit

Headless Code Editor MCP Server: trust score 20/100 — 2 capability surfaces.

Trust score

20

Grade F

Risk flags

  • Can modify files

    Restrict the working directory to a sandboxed path. Avoid pointing it at your home directory or repo with secrets.

  • Community-authored

    Maintained by oakenai. Confirm the repo and signing before installing.

Capability surface

  • Filesystem write

    High risk

    Can create, modify, or delete files on disk. High-impact if scope is broad.

    Evidence: editor

  • Browser automation

    High risk

    Drives a real browser (Playwright, Puppeteer). Can scrape any logged-in service.

    Evidence: headless

Trust signals

Total trust score is the sum of these contributions. Each signal carries a fixed weight.

  • Verified by Loadout

    +0 / 20

    Not in our manually-verified set yet.

  • Official author

    +0 / 15

    Maintained by community contributors.

  • Community traction

    +0 / 20

    No star data available.

  • Public source

    +15 / 15

    Source is publicly auditable.

  • Stability

    +0 / 15

    Stability not yet assessed.

  • Capability surface

    +5 / 15

    2 high-risk capabilities detected.

Disclaimer

This is an automated heuristic triage. It does not replace a hand-rolled code audit. Use it to prioritise which servers deserve a deeper look — especially anything carrying high-risk capabilities like shell execution or filesystem write.