Figma ファイル構造を分析するための MCP (Model Context Protocol) サーバー。
Figmaファイルを分析してノード階層を抽出する
REST APIとMCPプロトコルの両方をサポート
設定可能なノードツリーの深さ
Related MCP server: Figma MCP
Node.js 16以上
npmまたはyarn
Figma APIキー
npm install -g figma-mcp-servergit clone https://github.com/yourusername/mcp-figma.git
cd mcp-figma
npm install
npm run buildサンプル環境ファイルをコピーし、Figma API キーを追加します。
cp .env.example .env次に、 .envファイルを編集し、Figma API キーを追加します。
FIGMA_API_KEY=your_figma_api_key_hereFigma アカウント設定から Figma API キーを取得できます: https://www.figma.com/developers/api#access-tokens
サーバーを起動します。
npm startこれにより、ポート 3000 (または.envファイルで指定されたポート) で Express サーバーが起動します。
GET /health - ヘルスチェックエンドポイント
GET /openapi.json - OpenAPI仕様
GET /mcp.json - MCP マニフェスト
POST /analyze - Figma ファイルを解析する
分析エンドポイントへのリクエストの例:
curl -X POST http://localhost:3000/analyze \
-H "Content-Type: application/json" \
-d '{"figmaUrl": "https://www.figma.com/file/FILE_ID/PROJECT_NAME?node-id=NODE_ID", "depth": 2}'サーバーは、MCP プロトコルを介して LLM によって直接使用できます。
figma-mcp-server --cliまたはソースから実行する場合:
npm run start -- --cliシンプルなクライアントサンプルが含まれています。使い方は以下のとおりです。
node client-example.js https://www.figma.com/file/FILE_ID/PROJECT_NAME?node-id=NODE_ID 2最後のパラメータはオプションの深度パラメータです。
npm run devnpm testコンテナ化されたデプロイメント用に Dockerfile が提供されています。
docker build -t figma-mcp-server .
docker run -p 3000:3000 --env-file .env figma-mcp-serverマサチューセッツ工科大学
Analyze a Figma file structure to understand its nodes and hierarchy
| Name | Required | Description | Default |
|---|---|---|---|
| figmaUrl | Yes | The URL of the Figma file to analyze | |
| depth | No | Optional depth parameter to limit the node tree depth |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool analyzes structure but doesn't mention whether it's read-only, requires authentication, has rate limits, returns specific formats, or handles errors. For a tool with no annotation coverage, this leaves significant gaps in understanding its behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the purpose. It avoids redundancy and is appropriately sized for a simple tool, though it could be slightly more informative without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description is incomplete. It doesn't explain what the analysis returns, how nodes are structured, or any behavioral traits. For a tool that likely outputs complex hierarchical data, this lack of context makes it inadequate for full understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, so parameters are well-documented in the schema. The description adds minimal value beyond implying analysis of 'nodes and hierarchy', which relates to the depth parameter. It doesn't provide additional syntax or format details, so baseline 3 is appropriate as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('analyze') and resource ('Figma file structure'), specifying the goal is to 'understand its nodes and hierarchy'. It's specific about what the tool does, though without sibling tools, differentiation isn't needed. However, it's slightly vague on the exact output or analysis type beyond 'understand'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or constraints. It mentions analyzing file structure but doesn't specify use cases like design review, extraction, or debugging. With no sibling tools, this is less critical, but still lacks operational context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
analyze_figma_fileScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly distinct by default, as there are no other tools to confuse it with.
The single tool follows a clear verb_noun pattern (analyze_figma_file), and with only one tool, consistency is inherently perfect. There are no other tools to deviate from this pattern.
A single tool is too few for a server named 'Figma MCP Server,' which suggests a broader domain like Figma file management. This minimal set likely leaves significant gaps in functionality, such as creating, updating, or listing files, making it feel incomplete for the implied scope.
The tool surface is severely incomplete for a Figma server. It only provides analysis of file structure, missing essential operations like retrieving files, creating or editing designs, managing comments, or accessing other Figma resources, which are core to the domain.
The Figma MCP server brings Figma design context directly into your AI workflow.
Geometry and CAD file metadata extraction for STL, OBJ, PLY, PCD, LAS/LAZ, glTF/GLB.
smart-data-extractor MCP server on Cloudflare Workers · REST + MCP JSON-RPC · free tier
Access and maintain design system docs, tokens, components, skills, and contexts across any project.
