Evaluation report

• Repository is reachable

  https://github.com/rashidazarang/airtable-mcp @ 7bb1d7d — ★ 86 · TypeScript · MIT · last push 5 months ago

• Manifest detected

  kind=mcp slug=rashidazarang-airtable-mcp · source=package.json

• Slug is URL-safe

  "rashidazarang-airtable-mcp" matches /^[a-z0-9][a-z0-9-]{0,62}$/

• Slug is unique within kind

  No collision found for mcp/rashidazarang-airtable-mcp

• Version is semver

  4.0.1

• Description quality

  16 words · 147 chars — "Advanced AI-powered Airtable MCP server with TypeScript support, intelligent ana…"

• README is present and substantial

  13,052 chars · 15 sections · 8 code blocks

• Tags / topics declared

  16 total — airtable, mcp, claude, claude-desktop, anthropic, ai (+10)

• README has usage / example sections

  found: Quick Start · Quick Start · Usage

• Homepage / docs URL declared

  https://github.com/rashidazarang/airtable-mcp#readme

• Dependencies: known vulnerabilities

  OSV.dev clean — 0 high/critical across 4 deps

• 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: ESM packagewarn

  package.json missing "type": "module"

  Modern MCP servers are ESM. Add `"type": "module"` unless you have a CJS-only reason.

• MCP: launch path

  bin: airtable-mcp, airtable-mcp-cli · scripts.start

• MCP: @modelcontextprotocol/sdk in dependencies

  pinned at "^1.26.0"

• MCP: SDK version pinned

  pinned at "^1.26.0"

• MCP: server surface

  0 tools

• Recent activitywarn

  last push 5 months ago — looks slowing down

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

• 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.

• Tests detected

  1 test directory

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.