better-code-review-graph 3.1.0b1

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.

Features

Feature	code-review-graph	better-code-review-graph
Multi-word search	Broken (literal substring)	AND-logic word splitting
callers_of/callees_of	Empty results (bare name targets)	Qualified name resolution + bare fallback
Embedding	sentence-transformers + torch (1.1 GB)	qwen3-embed ONNX + LiteLLM (200 MB), dual-mode
Output size	Unbounded (500K+ chars)	Paginated (max_results, truncated flag)
Tool design	9 individual tools	5 tools: graph + query + review + config + help
Plugin hooks	Invalid PostEdit/PostGit	Valid PostToolUse

Quick Start

Claude Code Plugin (Recommended)

Via marketplace (includes skills: /refactor-check, /review-delta, /review-pr + hooks):

/plugin marketplace add n24q02m/claude-plugins
/plugin install better-code-review-graph@claude-plugins

Or install this plugin only:

/plugin marketplace add n24q02m/better-code-review-graph
/plugin install better-code-review-graph

Includes hooks (SessionStart auto-build, PostToolUse auto-update). Configure env vars in ~/.claude/settings.local.json or shell profile.

MCP Server

Option 1: uvx

{
  "mcpServers": {
    "better-code-review-graph": {
      "command": "uvx",
      "args": ["--python", "3.13", "better-code-review-graph"]
    }
  }
}

Other MCP clients (Cursor, Codex, Gemini CLI, Windsurf, Cline, Amp, OpenCode)

// Cursor (~/.cursor/mcp.json)
// Windsurf (~/.codeium/windsurf/mcp_config.json)
// Cline (cline_mcp_settings.json)
// Amp (~/.config/amp/settings.json)
// OpenCode (~/.opencode.json)
{
  "mcpServers": {
    "better-code-review-graph": {
      "command": "uvx",
      "args": ["--python", "3.13", "better-code-review-graph"]
    }
  }
}

# Codex (~/.codex/config.toml)
[mcp_servers.better-code-review-graph]
command = "uvx"
args = ["--python", "3.13", "better-code-review-graph"]

// Gemini CLI (~/.gemini/settings.json)
{
  "mcpServers": {
    "better-code-review-graph": {
      "command": "uvx",
      "args": ["--python", "3.13", "better-code-review-graph"]
    }
  }
}

Option 2: Docker

{
  "mcpServers": {
    "better-code-review-graph": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "-v", ".:/repo:ro", "n24q02m/better-code-review-graph:latest"]
    }
  }
}

Claude Code Plugin Details

When installed as a plugin, you get:

Hooks:

• SessionStart: Auto-builds the code graph when a conversation starts
• PostToolUse: Auto-updates the graph after file modifications (Write, Edit, Bash)

Skills:

• refactor-check: Safety analysis before refactoring -- dependency graph, blast radius
• review-delta: Review uncommitted changes using graph context
• review-pr: Review a pull request with structural analysis

Tools

graph -- Graph lifecycle

Actions: build | update | stats | embed

Action	Description
build	Full or incremental graph build. Set full_rebuild=true to re-parse all files.
update	Alias for build with full_rebuild=false (incremental).
stats	Graph size, languages, node/edge breakdown, embedding count.
embed	Compute vector embeddings for semantic search. Dual-mode: local ONNX or cloud LiteLLM.

query -- Graph queries

Actions: query | search | impact | large_functions

Action	Description
query	Predefined pattern queries: callers_of, callees_of, imports_of, importers_of, children_of, tests_for, inheritors_of, file_summary.
search	Search code entities by name/keyword or semantic similarity.
impact	Blast radius of changed files. Auto-detects from git diff. Paginated with max_results.
large_functions	Find functions/classes exceeding a line-count threshold.

review -- Code review context

Token-optimized review context with structural summary, source snippets, and review guidance. Auto-detects changed files from git diff.

config -- Server configuration

Actions: status | set | cache_clear

Action	Description
status	Server info: version, graph path, node/edge counts, embedding backend.
set	Update runtime settings (e.g., log_level).
cache_clear	Remove all computed embeddings.

help -- Full documentation

Topics: graph | query | review | config

Returns complete documentation for each tool. Use when the compressed descriptions above are insufficient.

Configuration

Variable	Default	Description
EMBEDDING_BACKEND	(auto-detect)	local or litellm
EMBEDDING_MODEL	gemini/gemini-embedding-001	LiteLLM model (when backend=litellm)
API_KEYS	-	LLM API keys (format: ENV_VAR:key,...). Enables LiteLLM.
LITELLM_PROXY_URL	-	LiteLLM Proxy URL. Enables LiteLLM via proxy.
LITELLM_PROXY_KEY	-	LiteLLM Proxy virtual key.

Embedding Backends

Backend	Config	Size	Description
local (default)	Nothing needed	~570 MB (first use)	qwen3-embed ONNX. Zero-config.
litellm	API_KEYS or LITELLM_PROXY_URL	0 MB	Cloud providers via LiteLLM.

• Auto-detection: API_KEYS or LITELLM_PROXY_URL set -> LiteLLM. Otherwise -> local ONNX.
• Override: EMBEDDING_BACKEND=local or EMBEDDING_BACKEND=litellm.
• Fixed 768-dim storage: Switching backends does NOT invalidate existing vectors.

Supported Languages

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

Ignore Files

Create .code-review-graphignore in your project root:

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

Security

• Graceful fallbacks -- Cloud embedding failure falls back to local ONNX
• Error handling -- Tools return error strings with fix suggestions, never crash
• Read-only mount -- Docker mode mounts repo as :ro (read-only)

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

Requirements: Python 3.13, uv

Compatible With

Also by n24q02m

Server	Description
wet-mcp	Web search, content extraction, and documentation indexing
mnemo-mcp	Persistent AI memory with hybrid search and cross-machine sync
better-notion-mcp	Markdown-first Notion API with 9 composite tools
better-email-mcp	Email (IMAP/SMTP) with multi-account and auto-discovery
better-godot-mcp	Godot Engine 4.x with 18 tools for scenes, scripts, and shaders
better-telegram-mcp	Telegram dual-mode (Bot API + MTProto) with 6 composite tools

Contributing

See CONTRIBUTING.md.

License

MIT -- See LICENSE.