Evaluation report

• Repository is reachable

  https://github.com/cafe3310/agent-skill-memories-off @ 414091d — ★ 40 · Python · Apache-2.0 · last push 6 weeks ago

• Manifest detected

  kind=mcp slug=mcp-server-memories-off · path=legacy/memories-off-mcp · source=package.json

• Slug is URL-safe

  "mcp-server-memories-off" matches /^[a-z0-9][a-z0-9-]{0,62}$/

• Slug is unique within kind

  No collision found for mcp/mcp-server-memories-off

• Version is semver

  2.0.3

• Description qualitywarn

  Only 4 words · 22 chars — more detail helps discovery

  Tell consumers what this artifact does in a full sentence.

• README is present and substantial

  2,973 chars · 6 sections · 4 code blocks

• Tags / topics declared

  12 total — mcp, modelcontextprotocol, memory, agent-skill-repository, agent-skills, cli (+6)

• README has usage / example sections

  no labeled section but 4 code blocks document usage

• Homepage / docs URL declared

  no homepage declared (registry will use the repo URL) — info-only, not blocking

• Dependencies: known vulnerabilitieswarn

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

  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: mcp-server-memories-off

• MCP: @modelcontextprotocol/sdk in dependencies

  pinned at "1.0.1"

• MCP: SDK version pinned

  pinned at "1.0.1"

• MCP: ESM package

  "type": "module"

• MCP: server surface

  0 tools

• 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.

• Recent activity

  last push 6 weeks ago

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.