design_patterns_mcp
apolosan/design_patterns_mcp
An intelligent Model Context Protocol (MCP) server providing access to nearly 700 design patterns using a hybrid search engine. It combines semantic, keyword, and graph-augmented retrieval to recommend ideal software architectural solutions through natural language.
Overview
The Design Patterns MCP server offers developers an advanced assistant for identifying and implementing software patterns across dozens of categories ranging from classic Gang of Four to cloud architecture, web3, and machine learning. By utilizing a hybrid search approach combining BM25, semantic embeddings over SQLite, and graph relationship traversal, it maps natural language problem statements directly to precise code patterns, solutions, and implementations.
Capabilities
- ▸Hybrid search (semantic + keyword BM25 + graph augmentation)
- ▸Extensive catalog of 686 patterns across 90+ categories
- ▸Detailed pattern retrieval with code examples
- ▸Multi-level caching and telemetry monitoring
- ▸STDIO and HTTP transport modes
Best for
Discovering suitable architectural or design patterns by describing a software problem in natural language., Querying specific GoF, microservices, cloud, or security patterns along with implementation details and code examples., Integrating design pattern advice directly into AI-assisted coding environments like Claude Desktop or Cursor.
Works with
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
実装・指示の品質。 — AIによるSKILL.md/README解析
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
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
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
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
コミュニティの採用度。 — GitHub Stars/Forks(対数スケール)
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
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 or via Docker container with standard local database access and optional HTTP transport mode.
Categories
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.