Evaluation report

• Repository is reachable

  https://github.com/arinspunk/claude-talk-to-figma-mcp @ c7adf24 — ★ 623 · TypeScript · MIT · last push 2 months ago

• Manifest detected

  kind=mcp slug=claude-talk-to-figma-mcp · source=package.json

• Slug is URL-safe

  "claude-talk-to-figma-mcp" matches /^[a-z0-9][a-z0-9-]{0,62}$/

• Slug is unique within kind

  No collision found for mcp/claude-talk-to-figma-mcp

• Version is semver

  1.0.0

• Description qualitywarn

  Only 6 words · 32 chars — more detail helps discovery

  Tell consumers what this artifact does in a full sentence.

• README has usage / example sectionswarn

  README has no Usage / Example / Quick start / Installation heading at any level

  Add a `# Usage`, `## Quick start`, or similar section so end users can copy/paste a working invocation. Code blocks alone work too if there are several.

• README is present and substantial

  7,944 chars · 10 sections · 1 code block

• Tags / topics declared

  14 total — claude, figma, mcp, plugin, ai, design (+8)

• Homepage / docs URL declared

  https://github.com/arinspunk/claude-talk-to-figma-mcp#readme

• Dependencies: known vulnerabilities

  OSV.dev clean — 0 high/critical across 1 dep

• 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: SDK version pinnedwarn

  @modelcontextprotocol/sdk pinned at "latest" — drifts on every install

  Pin to a caret range (e.g. `^1.2.0`) or an exact version so consumers reproduce your tested build.

• MCP: launch path

  bin: claude-talk-to-figma-mcp, claude-talk-to-figma-mcp-server, claude-talk-to-figma-mcp-socket · scripts.start

• MCP: @modelcontextprotocol/sdk in dependencies

  pinned at "latest"

• MCP: ESM package

  "type": "module"

• MCP: server surface

  0 tools

• Recent activity

  last push 2 months ago

• Tests detected

  1 test directory · 5 test files

• CI configuration detected

  GitHub Actions (2 workflows)

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.