MCP Safety Board

← All servers

MCP Safety Board · server report · November 2026

samuelgursky/davinci-resolve-mcp

B
88 / 100
Grade B · ★ 4,107 · Python 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 labelled1 of 45 tools whose name or description suggests delete, write or run declares neither destructiveHint nor readOnlyHint. −2 each.−2
Tools with any label427 of 445 tools (96%) carry any annotation; half or more.0
README install commandThe README tells users to launch the server with npx / bunx / uvx / pnpm dlx without a pinned version (or with @latest).−10
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).88
  • MCP106 (5): A destructive tool has no annotations (recorded only: already counted in the tool-label check). No points.

Changes that would raise this grade

  1. +10Pin the version in the README install command (pkg@1.2.3 or pkg==1.2.3, not @latest). Alone, this gives 98 (A).
  2. +2Label the 1 tool that deletes, writes or runs: add destructiveHint (or readOnlyHint) to its annotations. Alone, this gives 90 (A).

Doing all of these gives 100 (A).

What was checked

Commit checked
94acbd5ee901
Repository
github.com/samuelgursky/davinci-resolve-mcp
Tools found
445, of which 427 carry any label (96%)
Risky tools
45, of which 44 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

MCP safety: B
[![MCP safety: B](https://mcp-safety-board.pages.dev/badge/samuelgursky--davinci-resolve-mcp.svg)](https://mcp-safety-board.pages.dev/s/samuelgursky--davinci-resolve-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.