MCP Safety Board · server report · November 2026
ooples/token-optimizer-mcp
F
44 / 100
Grade F · ★ 579 · JavaScript checked by hand
How the score was worked out
| Check | What was found | Points |
|---|---|---|
| Risky tools labelled | 12 of 14 tools whose name or description suggests delete, write or run declare neither destructiveHint nor readOnlyHint. −2 each. | −24 |
| Tools with any label | 6 of 108 tools (6%) carry any annotation; fewer than half. | −10 |
| README install command | The README tells users to launch the server with npx / bunx / uvx / pnpm dlx without a pinned version (or with @latest). | −10 |
| Committed config: MCP003 | An MCP config file committed in the repo uses a moving tag (@latest or :latest). 9 found, at most 3 count. Medium: −4 each. | −12 |
| Score | 100 minus the penalties above (never below 0). | 44 |
Changes that would raise this grade
- +24Label the 12 tools that delete, write or run: add destructiveHint (or readOnlyHint) to their annotations. Alone, this gives 68 (D).
- +12Replace @latest / :latest in the committed MCP config with a fixed version (9 places). Alone, this gives 56 (F).
- +10Add annotations to 48 more tools so at least half of all 108 tools are labelled (labelling the risky tools above counts too). Alone, this gives 54 (F).
- +10Pin the version in the README install command (pkg@1.2.3 or pkg==1.2.3, not @latest). Alone, this gives 54 (F).
Doing all of these gives 100 (A).
What was checked
- Commit checked
7e29bbf005d3- Repository
- github.com/ooples/token-optimizer-mcp
- Tools found
- 108, of which 6 carry any label (6%)
- Risky tools
- 14, of which 2 labelled
- README install
- not pinned
- 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
[](https://mcp-safety-board.pages.dev/s/ooples--token-optimizer-mcp.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.