Evaluation report
Passingknowledge-rag · mcpf433745· 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/lyonzin/knowledge-rag @ f433745 — ★ 221 · Python · MIT · last push today
Manifest detected
kind=mcp slug=knowledge-rag · source=pyproject.toml
Slug is URL-safe
"knowledge-rag" matches /^[a-z0-9][a-z0-9-]{0,62}$/
Slug is unique within kind
No collision found for mcp/knowledge-rag
Version is semver
4.5.0
Documentation
5 passedDescription quality
23 words · 133 chars — "Local RAG System for Claude Code — Hybrid search + Cross-encoder Reranking + 13 …"
README is present and substantial
77,333 chars · 16 sections · 53 code blocks
Tags / topics declared
20 total — antigravity, claude, claude-code, claude-code-cli, codex, cursor-ai (+14)
README has usage / example sections
found: Installation · Usage · Quick Start
Homepage / docs URL declared
https://pypi.org/project/knowledge-rag/
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
1 test directory · 30 test files
CI configuration detected
GitHub Actions (6 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.