better-code-review-graph 1.0.0b2

Knowledge graph for token-efficient code reviews — fixed search, configurable embeddings, qualified call resolution

better-code-review-graph

mcp-name: io.github.n24q02m/better-code-review-graph

Knowledge graph for token-efficient code reviews -- fixed search, configurable embeddings, qualified call resolution.

Fork of code-review-graph with critical bug fixes, configurable embeddings, and production CI/CD. Parses your codebase with Tree-sitter, builds a structural graph of functions/classes/imports, and gives Claude (or any MCP client) precise context so it reads only what matters.

---

Why Better

Feature	code-review-graph	better-code-review-graph
Multi-word search	Broken (literal substring match)	AND-logic word splitting ("firebase auth" matches both verify_firebase_token and FirebaseAuth)
callers_of accuracy	Empty results (bare name targets)	Qualified name resolution -- same-file calls resolved to file::name
Embedding model	all-MiniLM-L6-v2 + torch (1.1 GB)	qwen3-embed ONNX + LiteLLM (200 MB)
Output size	Unbounded (500K+ chars possible)	Paginated (default 500 nodes, truncation metadata)
Plugin hooks	Invalid PostEdit/PostGit events	Valid PostToolUse (Write, Edit, Bash)
Plugin MCP	Duplicate registration (.mcp.json + plugin.json)	Single source (plugin.json only)
Python version	3.10+	3.13 (pinned)
CI/CD	GitHub Actions basic	PSR + Docker multi-arch + MCP Registry
Test coverage	Unknown	95%+ enforced

All fixes are submitted upstream as standalone PRs (see Upstream PRs). If all are merged, this repo will be archived.

---

Quick Start

Prerequisites

• Python 3.13 (required -- requires-python = "==3.13.*")

Option 1: uvx (Recommended)

{
  "mcpServers": {
    "better-code-review-graph": {
      "command": "uvx",
      "args": ["--python", "3.13", "better-code-review-graph", "serve"],
      "env": {
        // -- optional: cloud embeddings via LiteLLM
        // "API_KEYS": "GOOGLE_API_KEY:AIza...",
        // -- optional: LiteLLM Proxy (selfhosted gateway)
        // "LITELLM_PROXY_URL": "http://10.0.0.20:4000",
        // "LITELLM_PROXY_KEY": "sk-your-virtual-key"
        // -- without API_KEYS, uses built-in local qwen3-embed ONNX (zero-config)
      }
    }
  }
}

Option 2: pip

pip install better-code-review-graph
better-code-review-graph install   # creates .mcp.json in project root

Option 3: Docker

{
  "mcpServers": {
    "better-code-review-graph": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-v", "crg-data:/data",
        "-e", "API_KEYS",
        "n24q02m/better-code-review-graph:latest"
      ],
      "env": {
        // -- optional: cloud embeddings
        // "API_KEYS": "GOOGLE_API_KEY:AIza..."
      }
    }
  }
}

Option 4: Claude Code Plugin

claude plugin install n24q02m/better-code-review-graph@better-code-review-graph

Then open your project and tell Claude:

Build the code review graph for this project

---

MCP Tools

Claude uses these automatically once the graph is built.

Tool	Description
build_or_update_graph_tool	Build or incrementally update the graph. Default: incremental (changed files only).
get_impact_radius_tool	Blast radius of changed files. Shows which functions, classes, files are affected. Paginated with max_results.
get_review_context_tool	Token-optimized review context with structural summary, source snippets, and review guidance.
query_graph_tool	Predefined queries: callers_of, callees_of, imports_of, importers_of, children_of, tests_for, inheritors_of, file_summary.
semantic_search_nodes_tool	Search code entities by name/keyword or semantic similarity (requires embeddings).
embed_graph_tool	Compute vector embeddings for semantic search. Uses dual-mode backend.
list_graph_stats_tool	Graph size, languages, node/edge breakdown, embedding count.
get_docs_section_tool	Retrieve specific documentation sections for minimal token usage.
find_large_functions_tool	Find functions/classes exceeding a line-count threshold for decomposition audits.

---

Embedding Backends

Embeddings enable semantic search (vector similarity instead of keyword matching). Two backends are available:

Backend	Config	Size	Description
local (default)	Nothing needed	~570 MB (first use)	qwen3-embed ONNX. Zero-config. Downloaded on first embed_graph_tool call.
litellm	API_KEYS or LITELLM_PROXY_URL	0 MB	Cloud providers via LiteLLM (Gemini, OpenAI, Cohere, etc.).

• Auto-detection: If API_KEYS or LITELLM_PROXY_URL is set, uses LiteLLM. Otherwise, uses local ONNX.
• Override: Set EMBEDDING_BACKEND=local or EMBEDDING_BACKEND=litellm explicitly.
• Fixed 768-dim storage: All embeddings stored at 768 dimensions via MRL truncation. Switching backends does NOT invalidate existing vectors.
• Lazy loading: Model downloads on first embed call, not on server start.

---

CLI Reference

better-code-review-graph install     # Register MCP server with Claude Code (creates .mcp.json)
better-code-review-graph init        # Alias for install
better-code-review-graph build       # Full graph build (parse all files)
better-code-review-graph update      # Incremental update (changed files only)
better-code-review-graph watch       # Auto-update on file changes
better-code-review-graph status      # Show graph statistics
better-code-review-graph serve       # Start MCP server (stdio transport)

---

Configuration

Variable	Default	Description
EMBEDDING_BACKEND	(auto-detect)	local (qwen3-embed ONNX) or litellm (cloud API). Auto: API_KEYS/proxy -> litellm, else local.
EMBEDDING_MODEL	gemini/gemini-embedding-001	LiteLLM embedding model (only used when backend=litellm).
API_KEYS	-	LLM API keys for SDK mode (format: ENV_VAR:key,...). Enables LiteLLM backend.
LITELLM_PROXY_URL	-	LiteLLM Proxy URL. Enables LiteLLM backend via proxy.
LITELLM_PROXY_KEY	-	LiteLLM Proxy virtual key.

Ignore files

Create .code-review-graphignore in your project root to exclude paths:

generated/**
*.generated.ts
vendor/**
node_modules/**

---

Supported Languages

Python, TypeScript, JavaScript, Go, Rust, Java, C#, Ruby, Kotlin, Swift, PHP, C/C++

Each language has full Tree-sitter grammar support for functions, classes, imports, call sites, inheritance, and test detection.

---

Cross-Agent Compatibility

Feature	Claude Code	Copilot CLI	Codex	Gemini CLI	Antigravity	OpenCode	Cursor	Windsurf	Cline	Amp
MCP tools (9 tools)	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes
CLAUDE.md / AGENTS.md	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	--	--
Skills (slash commands)	Yes	Yes	Yes	Yes	--	Yes	--	--	--	--
Hooks (PostToolUse)	Yes	--	Yes	Yes	--	--	--	--	--	--
Plugin (marketplace)	Yes	Yes	--	--	--	--	--	--	--	--

---

Upstream PRs

All fixes in this fork are submitted as standalone PRs to the original code-review-graph:

• #37 -- Multi-word search AND logic
• #38 -- Parser call target resolution (fixes #20)
• #39 -- Impact radius output pagination

If all upstream PRs are merged, this repository will be archived.

---

Build from Source

git clone https://github.com/n24q02m/better-code-review-graph
cd better-code-review-graph
uv sync --group dev
uv run pytest
uv run better-code-review-graph serve

Requirements: Python 3.13 (not 3.14+), uv

---

Compatible With

Also by n24q02m

Server	Description	Install
wet-mcp	Web search, content extraction, library docs	uvx --python 3.13 wet-mcp@latest
mnemo-mcp	Persistent AI memory with hybrid search	uvx mnemo-mcp@latest
better-notion-mcp	Notion API for AI agents	npx -y @n24q02m/better-notion-mcp@latest
better-email-mcp	Email (IMAP/SMTP) for AI agents	npx -y @n24q02m/better-email-mcp@latest
better-godot-mcp	Godot Engine for AI agents	npx -y @n24q02m/better-godot-mcp@latest
better-telegram-mcp	Telegram Bot API + MTProto for AI agents	uvx --python 3.13 better-telegram-mcp@latest

License

MIT - See LICENSE