trace-mcp
MCP Servernikolai-vysotskyi/trace-mcp
trace-mcp is a Model Context Protocol server that creates a precomputed framework-aware dependency graph for codebases and knowledge vaults, reducing token usage and redundant tool calls by up to 50%.
98 15MITUpdated 2026-08-11
80
GreatOverview
trace-mcp solves the AI agent recomputation leak by indexing source code and markdown vaults into a structured dependency graph served via MCP. Rather than repeatedly reading files and guessing relationships across languages or frameworks, AI agents use specialized tools like `get_change_impact`, `search`, and `get_outline` to retrieve exact structural context instantly.
Capabilities
- ▸Framework-aware dependency graph creation and edge traversal
- ▸Cross-language code symbol search and usage discovery
- ▸Change impact analysis and reverse dependency tracing
- ▸Code-linked decision memory and knowledge graph search
- ▸Markdown vault and wikilink integration
Best for
Navigating large codebases without wasting tokens on manual file reads and grep commands, Assessing the blast radius of code changes across multi-language projects and frameworks, Querying code-linked architectural decisions and cross-session development history, Indexing and querying markdown knowledge vaults with full wikilink and tag awareness
Works with
Claude CodeCursorGitHub Copilot
Evoa Score breakdown= Σ (score × weight)
80Task 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%43 → +5.2
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%53 → +4.2
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 total79.8 / 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
The skill operates by reading local source code and knowledge files to build an internal index, requiring standard filesystem read permissions for the target repository or vault.
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.