contextplus

Name: contextplus
Rating: 84 (1 reviews)
Author: forloopcodes

MCP Server

forloopcodes/contextplus

Context+ is an advanced Model Context Protocol (MCP) server that provides semantic intelligence, RAG-based code search, AST structural analysis, and Obsidian-style feature linking for large-scale codebases.

2k 167MITUpdated 2026-07-13

Great

View on GitHub Open source file

Overview

Context+ bridges the gap between massive codebases and AI code assistants by transforming raw code into a searchable, hierarchical feature graph. It uses Tree-sitter AST parsing, spectral clustering, and vector embeddings (via Ollama or OpenAI-compatible backends) to offer precise semantic code navigation, dependency tracing, change validation, and long-term memory management for developers demanding high accuracy.

Capabilities

▸Semantic code search and identifier retrieval
▸Tree-sitter AST structural code tree generation
▸Spectral clustering for semantic code navigation
▸Impact analysis and blast radius calculation
▸Shadow restore point version control and rollback
▸Obsidian-style feature hub linking with wikilinks
▸Graph-based persistent memory and RAG context management
▸Static analysis runner across multiple languages

Best for

Navigating and searching large, unfamiliar codebases using natural language semantics., Tracing symbol references and calculating code change blast radii across projects., Maintaining persistent architectural documentation and interlinked concept memory nodes for AI workflows., Validating code modifications and managing safe rollbacks through shadow restore points.

Works with

Claude CodeCursorOpenCode

Evoa Score breakdown= Σ (score × weight)

Task usefulness20%100 → +20.0

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%85 → +12.8

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%58 → +7.0

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%84 → +6.7

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

Compatibility5%75 → +3.8

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 total84.2 / 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

Context+ operates locally or communicates with specified embedding provider endpoints. It handles codebase contents and code modifications, utilizing local shadow restore points for rollback safety.