Better Code Review Graph

Knowledge graph for efficient code reviews with advanced search and context 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.

<!-- Badge Row 1: Status -->

CI codecov PyPI Docker License: MIT

<!-- Badge Row 2: Tech -->

Python MCP semantic-release Renovate

<!-- Glama badge --> <a href="https://glama.ai/mcp/servers/n24q02m/better-code-review-graph"> <img width="380" height="200" src="https://glama.ai/mcp/servers/n24q02m/better-code-review-graph/badge" alt="better-code-review-graph MCP server" /> </a>

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

Featurecode-review-graphbetter-code-review-graph
Multi-word searchBroken (literal substring)AND-logic word splitting
callers_of/callees_ofEmpty results (bare name targets)Qualified name resolution + bare fallback
Embeddingsentence-transformers + torch (1.1 GB)qwen3-embed ONNX + cloud (200 MB), dual-mode
Output sizeUnbounded (500K+ chars)Paginated (max_results, truncated flag)
Tool design9 individual tools6 tools: graph + query + review + config + setup + help
Plugin hooksInvalid PostEdit/PostGitValid PostToolUse

Setup

With AI Agent -- copy and send this to your AI agent:

Please set up better-code-review-graph for me. Follow this guide: https://raw.githubusercontent.com/n24q02m/better-code-review-graph/main/docs/setup-with-agent.md

Manual Setup -- follow docs/setup-manual.md

Tools

graph -- Graph lifecycle

Actions: build | update | stats | embed

ActionDescription
buildFull or incremental graph build. Set full_rebuild=true to re-parse all files.
updateAlias for build with full_rebuild=false (incremental).
statsGraph size, languages, node/edge breakdown, embedding count.
embedCompute vector embeddings for semantic search. Dual-mode: local ONNX or cloud.

query -- Graph queries

Actions: query | search | impact | large_functions

ActionDescription
queryPredefined pattern queries: callers_of, callees_of, imports_of, importers_of, children_of, tests_for, inheritors_of, file_summary.
searchSearch code entities by name/keyword or semantic similarity.
impactBlast radius of changed files. Auto-detects from git diff. Paginated with max_results.
large_functionsFind 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

ActionDescription
statusServer info: version, graph path, node/edge counts, embedding backend.
setUpdate runtime settings (e.g., log_level).
cache_clearRemove all computed embeddings.

setup -- Credential setup

Actions: status | start | skip | reset | complete

ActionDescription
statusShow current credential state and setup URL.
startStart relay setup to configure API keys via browser.
skipSet local mode (skip relay permanently, use ONNX only).
resetClear credentials and reset state.
completeRe-resolve credentials from environment variables.

help -- Full documentation

Topics: graph | query | review | config

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

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

License

MIT -- See LICENSE.