MCP Safety Board

← All servers

MCP Safety Board · server report · November 2026

cyberkaida/reverse-engineering-assistant

D
62 / 100
Grade D · ★ 961 · Java checked by hand

How the score was worked out

Starts at 100. Each line shows a check from the method and the points it took off.
CheckWhat was foundPoints
Risky tools labelled14 of 14 tools whose name or description suggests delete, write or run declare neither destructiveHint nor readOnlyHint. −2 each.−28
Tools with any label0 of 88 tools (0%) carry any annotation; fewer than half.−10
README install commandThe README has no npx / bunx / uvx / pnpm dlx launch command, so there is nothing to pin.0
Committed configNo committed MCP config with an unpinned package, a moving tag, a broad filesystem root, a privileged docker server or plain http.0
Score100 minus the penalties above (never below 0).62

Changes that would raise this grade

  1. +28Label the 14 tools that delete, write or run: add destructiveHint (or readOnlyHint) to their annotations. Alone, this gives 90 (A).
  2. +10Add annotations to 44 more tools so at least half of all 88 tools are labelled (labelling the risky tools above counts too). Alone, this gives 72 (C).

Doing all of these gives 100 (A).

What was checked

Commit checked
4d2fc5b4c5f4
Repository
github.com/cyberkaida/reverse-engineering-assistant
Tools found
88, of which 0 carry any label (0%)
Risky tools
14, of which 0 labelled
README install
no npx/uvx snippet
Last push
2026-11-14

Static reading of this one commit. No code was installed or run. This is a hygiene grade, not a security audit.

Maintainer?

Fixed something, or think a count is wrong? Request a re-check (opens a GitHub issue). Re-checks run on the latest commit.

README badge

MCP safety: D
[![MCP safety: D](https://mcp-safety-board.pages.dev/badge/cyberkaida--reverse-engineering-assistant.svg)](https://mcp-safety-board.pages.dev/s/cyberkaida--reverse-engineering-assistant.html)

Want a written review of your agent's tools and permissions?

48-hour written review. Which tools your agent can call, what each one can change, which need a confirmation step, and what to lock down first. Send a message to start.