#
ENJA

code-review-graph

MCP Server

tirth8205/code-review-graph

Optimize AI code reviews and exploration using a structural codebase graph powered by Tree-sitter and the Model Context Protocol (MCP).

30k 2.8kMITUpdated 2026-08-02
View on GitHubOpen source file

Overview

Code Review Graph builds a structural map of a codebase using Tree-sitter, mapping functions, classes, imports, and calls into a local graph database. By integrating via the Model Context Protocol (MCP), it enables AI coding assistants to perform semantic searches, assess change blast radiuses, and retrieve precise code context without burning excessive tokens reading entire files.

Capabilities

  • ▸Semantic node search
  • ▸Blast radius and impact analysis
  • ▸Automated change detection and risk scoring
  • ▸Architecture and community overview mapping
  • ▸Test coverage mapping

Best for

Conducting risk-scored code reviews with minimal token consumption, Tracing code relationships like callers, callees, and dependencies, Assessing the impact radius and affected execution flows of a proposed change, Exploring large codebases semantically without manual Grep or Glob scans

Works with

Claude CodeCursorGitHub CopilotGemini CLIOpenCode
Evoa Score breakdown= Σ (score × weight)
85
Task usefulness20%88 → +17.6

実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析

Code quality15%90 → +13.5

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%100 → +15.0

リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ

Documentation12%42 → +5.0

ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量

Security15%80 → +12.0

危険・不審な挙動が無いか。 — AIによるセキュリティレビュー

Originality10%85 → +8.5

ありふれたラッパーではない独自性。 — AIによる独自性判定

Popularity8%100 → +8.0

コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）

Compatibility5%100 → +5.0

対応AIエージェントの広さ。 — AIによる対応エージェント判定

Weighted total84.6 / 100

ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →

Security considerations

Runs locally against your repository codebase using local file parsing and graph databases; ensure you review repository permissions when installing hooks.

Categories

CodingAI EngineeringDevOpsProductivity

Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.