n24q02m

better-code-review-graph

Community n24q02m
Updated

Knowledge graph for token-efficient code reviews โ€” fixed search, qualified call resolution, dual-mode embedding (ONNX + LiteLLM)

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.

CIcodecovPyPIDockerLicense: MIT

PythonMCPsemantic-releaseRenovate

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

Claude DesktopClaude CodeCursorVS Code CopilotAntigravityGemini CLIOpenAI CodexOpenCode

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

MCP Server ยท Populars

MCP Server ยท New

    globau

    Firefox DevTools MCP

    Model Context Protocol server for Firefox DevTools - enables AI assistants to inspect and control Firefox browser through the Remote Debugging Protocol

    Community globau
    lyonzin

    Knowledge RAG

    Local RAG System for Claude Code โ€” Hybrid search + Cross-encoder Reranking + Markdown-aware Chunking + 12 MCP Tools. No external servers, pure ONNX in-process.

    Community lyonzin
    nukeop

    nuclear

    Streaming music player that finds free music for you

    Community nukeop
    qualixar

    SuperLocalMemory V3

    World's first local-only AI memory to break 74% retrieval and 60% zero-LLM on LoCoMo. No cloud, no APIs, no data leaves your machine. Additionally, mode C (LLM/Cloud) - 87.7% LoCoMo. Research-backed. arXiv: 2603.14588

    Community qualixar
    proxy-intell

    Facebook Ads Library MCP Server

    MCP Server for Facebook ADs Library - Get instant answers from FB's ad library

    Community proxy-intell