Knowledge graph for token-efficient code reviews with fixed search and configurable embeddings
io.github.n24q02m/better-code-review-graph
https://github.com/n24q02m/better-code-review-graph.git
STDIO
No auth required
How models use it and what it is built for.
Knowledge graph for token-efficient code reviews with fixed search and configurable embeddings
Hosted endpoint — paste into any MCP client.
Configuration this server reads at startup.
Embedding backend override: 'local' (qwen3-embed ONNX) or 'litellm' (cloud). Auto-detected if omitted.
API keys for LiteLLM cloud embedding (format: ENV_VAR:key). Enables LiteLLM backend.
LiteLLM Proxy URL for self-hosted gateway. Enables LiteLLM backend via proxy.
LiteLLM Proxy virtual key.
API keys for LiteLLM cloud embedding (format: ENV_VAR:key)
Where to find authoritative docs and source for better-code-review-graph.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 30+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent Studio