figma-mcp
Model Context Protocol integration for the Figma API, enabling AI applications to access Figma files, components, and design tokens.
README
Figma MCP Server
Model Context Protocol integration for the Figma API. Brings Figma files, components, and design tokens into any MCP-compatible AI application.
Features
- File Operations: Get file structure, list files, export files
- Component Management: List components, get component details, search components
- Tokens & Variables: Access design tokens and variables
- Team & Project Tools: List teams, projects, and collaborate
- Design System Access: Retrieve design system information
- Real-time Capabilities: Watch file changes, get version history
Installation
From PyPI
pip install figma-mcp
From Source
git clone https://github.com/yourusername/figma-mcp.git
cd figma-mcp
pip install -e .
Development Installation
pip install -e ".[dev]"
Configuration
1. Get Your Figma API Token
- Go to Figma Settings → Account
- Create a personal access token
- Save it securely
2. Configure for Hermes
Add to ~/.hermes/config.yaml:
mcp_servers:
figma:
command: "python"
args: ["-m", "figma_mcp"]
env:
FIGMA_API_TOKEN: "${FIGMA_API_TOKEN}"
timeout: 120
connect_timeout: 30
3. Set Environment Variable
Create ~/.hermes/.env:
FIGMA_API_TOKEN=your_personal_access_token_here
4. Register with Hermes
hermes mcp add figma --command python --args -m figma_mcp
hermes mcp test figma
hermes mcp list
Available Tools
Files
- get_file - Retrieve full file structure and metadata
- get_file_nodes - Get specific nodes from a file
- list_files - List files in a team
- get_file_versions - Get version history of a file
- export_node - Export node as PNG/SVG/PDF
Components
- list_components - List all components in a file
- get_component - Get component details
- search_components - Search components by name
- get_component_sets - Get component sets/variants
Variables & Tokens
- list_variables - List design variables
- get_variable - Get variable details
- list_local_variables - List variables in a file
Team & Projects
- list_teams - List accessible teams
- list_projects - List projects in a team
- list_team_components - List components across team
Design Systems
- get_design_system - Retrieve design system info
- list_design_system_files - List design system files
Usage Examples
With Hermes CLI
# List all Figma files in your workspace
hermes ask "What Figma files do I have? Use the figma tools."
# Get component details
hermes ask "Show me all button components from my design system using get_component_sets"
# Export a design
hermes ask "Export the 'HomeScreen' node from file abc123xyz as PNG"
Programmatic Use
from figma_mcp import FigmaClient
client = FigmaClient(api_token="your_token")
# Get file
file_data = await client.get_file("file_id")
print(file_data["name"])
# List components
components = await client.list_components("file_id")
for comp in components:
print(f"Component: {comp['name']}")
API Reference
Authentication
All requests require a valid FIGMA_API_TOKEN environment variable.
Tool Inputs
Each tool accepts a JSON object with parameters. Example:
{
"file_key": "abc123xyz",
"ids": ["1:2", "3:4"]
}
Tool Outputs
All tools return JSON with:
{
"result": "success data",
"error": null
}
Or on error:
{
"result": null,
"error": "Error message"
}
Development
Run Tests
pytest tests/ -v
Type Checking
mypy figma_mcp/
Format Code
black figma_mcp/
isort figma_mcp/
Lint
ruff check figma_mcp/
Architecture
figma_mcp/
├── server.py # MCP Server entry point
├── client.py # Figma API client
├── tools/
│ ├── files.py # File operations
│ ├── components.py # Component tools
│ ├── variables.py # Variables & tokens
│ ├── teams.py # Team tools
│ └── design_systems.py
├── models.py # Pydantic models
├── errors.py # Custom exceptions
└── utils.py # Utilities
Troubleshooting
"MCP server is not connected"
hermes mcp test figma
Check the error output. Most common issues:
- Invalid token: Verify
FIGMA_API_TOKENis set correctly - Network error: Ensure you can reach
api.figma.com - Version mismatch: Update MCP SDK:
pip install --upgrade mcp
"Tool call timed out"
Increase timeout in config:
mcp_servers:
figma:
timeout: 300
connect_timeout: 60
"Permission denied"
Your token may lack scopes. Regenerate with all permissions enabled.
Limitations
- Personal access tokens can't access private/shared files outside your workspace
- Some endpoints require specific team/project permissions
- Real-time subscriptions not currently supported (batch polling instead)
Roadmap
- [ ] Real-time file change subscriptions
- [ ] Webhook support for file updates
- [ ] Batch operations
- [ ] File upload/creation
- [ ] Prototype and interaction data
- [ ] Constraint and interaction details
- [ ] Plugin API integration
Contributing
Contributions are encouraged! Please:
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-tool) - Add tests for your changes
- Submit a pull request
License
MIT License - see LICENSE file for details
Related Resources
Support
- 📖 Documentation
- 🐛 Issues
- 💬 Discussions
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。