← Index

io.github.n24q02m/better-code-review-graph

io.github.n24q02m/better-code-review-graph·v3.17.1·Search

Knowledge graph for token-efficient code reviews with fixed search and configurable embeddings

Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

Environment variables
EMBEDDING_BACKEND

Embedding backend override: 'local' (qwen3-embed ONNX) or 'litellm' (cloud). Auto-detected if omitted.

API_KEYS
secret

API keys for LiteLLM cloud embedding (format: ENV_VAR:key). Enables LiteLLM backend.

LITELLM_PROXY_URL

LiteLLM Proxy URL for self-hosted gateway. Enables LiteLLM backend via proxy.

LITELLM_PROXY_KEY
secret

LiteLLM Proxy virtual key.

API_KEYS
secret

API keys for LiteLLM cloud embedding (format: ENV_VAR:key)

MCP quality score · maturity, not trust · methodology
freshness
25
completeness
10
installability
25
documentation
15
stability
10
Alternatives in Search