Evaluation report
Passingcrewai · mcpfc41c42· 3 months ago
Every check MetaHub ran on this artifact, grouped by area. Static checks run on the source at publish time; behavioral checks run the artifact in a sandbox and judge what it actually does.
Structural
5 passedRepository is reachable
https://github.com/crewAIInc/crewAI @ fc41c42 — ★ 55,097 · Python · MIT · last push today
Manifest detected
kind=mcp slug=crewai · path=lib/crewai · source=pyproject.toml
Slug is URL-safe
"crewai" matches /^[a-z0-9][a-z0-9-]{0,62}$/
Slug is unique within kind
No collision found for mcp/crewai
Version is semver
0.1.0
Documentation
5 passedDescription quality
22 words · 193 chars — "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By …"
README is present and substantial
33,825 chars · 13 sections · 25 code blocks
Tags / topics declared
5 total — agents, ai, ai-agents, aiagentframework, llms
README has usage / example sections
found: Getting Started · Getting Started · Example
Homepage / docs URL declared
https://crewai.com
Safety
2 passedLICENSE file at repo root
LICENSE
No sensitive files in the repo
scanned for .env, credentials.json, *.pem, .ssh/, AWS / GCP configs — none found
Kind-specific
4 passedMCP: launch path
launch declared in pyproject.toml
MCP: @modelcontextprotocol/sdk in dependencies
non-Node server (pyproject.toml) — uses its language's MCP SDK
MCP: ESM package
non-Node server (pyproject.toml) — n/a
MCP: server surface
0 tools
Maintenance
3 passedRecent activity
last push today
Tests detected
6 test directories · 309 test files
CI configuration detected
GitHub Actions (14 workflows)
Behavioral
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.