Evaluation report
Passingopenai-example · mcpa0f37a7· 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/ComposioHQ/composio @ a0f37a7 — ★ 29,169 · TypeScript · MIT · last push today
Manifest detected
kind=mcp slug=openai-example · path=ts/examples/openai · source=package.json
Slug is URL-safe
"openai-example" matches /^[a-z0-9][a-z0-9-]{0,62}$/
Slug is unique within kind
No collision found for mcp/openai-example
Version is semver
0.1.10-alpha.0
Documentation
5 passedDescription quality
9 words · 59 chars — OK but more detail helps
README is present and substantial
8,800 chars · 8 sections · 7 code blocks
Tags / topics declared
17 total — agentic-ai, agents, ai, ai-agents, aiagents, developer-tools (+11)
README has usage / example sections
found: Quickstart
Homepage / docs URL declared
https://docs.composio.dev
Safety
3 passedDependencies: 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
Kind-specific
5 passedMCP: launch path
scripts.start
MCP: @modelcontextprotocol/sdk in dependencies
pinned at "catalog:"
MCP: SDK version pinned
pinned at "catalog:"
MCP: ESM package
"type": "module"
MCP: server surface
0 tools
Maintenance
3 passedRecent activity
last push today
Tests detected
21 test directories · 263 test files
CI configuration detected
GitHub Actions (32 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.