Evaluation report

• Repository is reachable

  https://github.com/AgentDeskAI/browser-tools-mcp @ d298068 — ★ 7,267 · JavaScript · MIT · last push 4 months ago

• Manifest detected

  kind=mcp slug=agentdeskai-browser-tools-server · path=browser-tools-server · source=package.json

• Slug is URL-safe

  "agentdeskai-browser-tools-server" matches /^[a-z0-9][a-z0-9-]{0,62}$/

• Slug is unique within kind

  No collision found for mcp/agentdeskai-browser-tools-server

• Version is semver

  1.2.0

• Description quality

  13 words · 87 chars — OK but more detail helps

• README is present and substantial

  10,927 chars · 10 sections · 1 code block

• Tags / topics declared

  12 total — browser, tools, debugging, logging, screenshots, chrome (+6)

• README has usage / example sections

  found: Quickstart · Installation · Usage

• Homepage / docs URL declared

  https://agentdesk.ai/

• Dependencies: known vulnerabilitieswarn

  3 high/critical advisories — @modelcontextprotocol/[email protected] (HIGH: GHSA-8r9q-7v3j-jr4g) · @modelcontextprotocol/[email protected] (HIGH: GHSA-w48q-cv73-mx4w) (+1)

  Update the affected packages, then re-publish. (`npm audit` shows the same data locally.)

• LICENSE file at repo root

  LICENSE

• No sensitive files in the repo

  scanned for .env, credentials.json, *.pem, .ssh/, AWS / GCP configs — none found

• MCP: launch path

  bin: browser-tools-server · scripts.start

• MCP: @modelcontextprotocol/sdk in dependencies

  pinned at "^1.4.1"

• MCP: SDK version pinned

  pinned at "^1.4.1"

• MCP: ESM package

  "type": "module"

• MCP: server surface

  0 tools

• Recent activitywarn

  last push 4 months ago — looks slowing down

  Consumers prefer artifacts that are actively maintained (threshold: 90 days, configurable via EVAL_RECENCY_PASS_DAYS).

• Tests detectedwarn

  no test/tests/__tests__/spec/t/ dirs, no JVM src/test/, and no JS/TS/Python/Go/Ruby/Elixir test files

  Add tests (even a smoke test). Consumers gauge maintenance quality by their presence.

• CI configuration detectedwarn

  no CI config found (looked for GitHub Actions, CircleCI, GitLab CI, etc.)

  Add a simple workflow (lint + test on PR) — it tells consumers the artifact is built reproducibly.

This artifact hasn't produced behavioral results yet: the evaluation sandbox couldn't run it (it may need credentials we don't provide, or a build our environment doesn't support). That's a limitation of our environment, not a verdict on the artifact.