#
ENJA

excalidraw-mcp

lesleslie/excalidraw-mcp

An AI-powered live visual diagramming tool combining a Python FastMCP backend with a TypeScript and React Excalidraw canvas stack.

14 5BSD-3-ClauseUpdated 2026-08-12

Overview

This hybrid architecture MCP server enables AI agents like Claude to directly manipulate and create visual diagrams on a real-time Excalidraw canvas. It bridges Python-based MCP protocol handling with a TypeScript Express backend and React frontend, instantly broadcasting changes via WebSockets to all connected clients.

Capabilities

  • Create geometric shapes such as rectangles, ellipses, and diamonds
  • Generate text elements, arrows, and lines on the canvas
  • Perform batch operations to create multiple elements simultaneously
  • Manage, update, delete, group, and query canvas elements with filters
  • Real-time WebSocket synchronization across multiple connected browser clients

Best for

Generating architectural diagrams or flowcharts automatically via AI prompts, Collaborative whiteboard sessions where AI assists in creating and structuring visual layouts, Visualizing complex multi-step processes or data structures in real-time

Works with

Claude CodeCursorGitHub Copilot
Evoa Score breakdown= Σ (score × weight)
76
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%27 → +3.2

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%35 → +2.8

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 total76.4 / 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

Canvas security settings such as JWT authentication, CORS, and rate limiting are environment-driven. Ensure secrets and tokens are properly managed and not committed to source control.

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.