Which integrations are available for this server?

Allows importing prompts from Figma frames using the Figma API, converting PROMPT/ frames into structured prompt JSON. Provides an MCP server for listing, validating, and exporting prompts for use with the Hermes prompt system.

How do I use Hermes Figma Prompt Hub MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Hermes Figma Prompt Hub MCP Server list all active prompts" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Hermes Figma Prompt Hub MCP Server

by jozrftamson

Overview Schema Source Related Servers Discussions Admin

Python

Local

Hermes Figma Prompt Hub - Complete Platform

Design System & Prompt Management Platform with Figma Integration

License: MIT GitHub Actions

🎯 Features

📊 Core Features

✅ Figma Integration — Import PROMPT/* frames directly from Figma
✅ Design System — Complete CSS/SCSS generation from design tokens
✅ Validation Suite — Schema, layer contract, and quality checks
✅ Prompt Management — Create, edit, validate, and version prompts
✅ Auto-Sync — Webhook-based auto-sync from Figma changes
✅ Web UI — Nuxt 3 dashboard for prompt management

🎨 Design System

Colors — Primary, Secondary, Semantic, Neutral palettes with shades
Typography — 8-level font scale with weights and line-heights
Spacing — 24-step spacing system (4px base)
Radius — 9-level border radius scale
Shadows — 5-level elevation system
Responsive — Mobile-first 12-column grid with breakpoints

🤖 Prompt Strategies

Chain-of-Thought — Structured step-by-step reasoning
Few-Shot Learning — Pattern recognition with examples
Role-Play Persona — Expert advice from specific roles
Tree-of-Thought — Multiple parallel solution paths
Meta-Reasoning — Self-validation and reflection

✅ Validation

Schema Validator — JSON schema compliance
Layer Contract — Figma structure validation
Content Quality — Clarity, specificity, token estimation
Strategy-Specific — Rules per prompting strategy

🔄 Integration

Figma API — Direct import from Figma files
Webhooks — Auto-sync on file changes
GitHub — Native git integration
CI/CD — GitHub Actions workflows

Related MCP server: Figma MCP Server

📦 Project Structure

hermes-figma-prompt-hub-nuxt/
├── pages/                    # Nuxt pages
│   ├── index.vue            # Dashboard
│   └── prompts/
│       ├── index.vue        # Prompts list
│       └── [id].vue         # Prompt detail
├── components/              # Vue components
├── stores/                   # Pinia stores
├── server/
│   ├── api/                 # Nuxt API routes
│   └── middleware/          # Server middleware
├── scripts/                 # Python & Bash scripts
│   ├── figma_importer.py    # Figma API client
│   ├── figma_webhook.py     # Webhook handler
│   ├── schema_validator.py  # Validation
│   ├── css_generator.py     # CSS generation
│   └── figma_sync.sh        # CLI orchestrator
├── data/                    # Design system JSON
│   ├── figma_design_system_extended.json
│   └── integration_guide.json
├── css/                     # Generated CSS
├── scss/                    # Generated SCSS
└── docs/                    # Documentation

🚀 Quick Start

Prerequisites

Node.js 18+
Python 3.10+
Git

Installation

# Clone repository
git clone https://github.com/jozrftamson/hermes-figma-prompt-hub-nuxt
cd hermes-figma-prompt-hub-nuxt

# Install dependencies
npm install

# Setup environment
cp .env.example .env.local
# Edit .env.local with your Figma credentials

Environment Variables

# .env.local
NUXT_FIGMA_API_TOKEN=figd_xxxx...
NUXT_FIGMA_FILE_ID=ABC123DEF456
NUXT_FIGMA_TEAM_ID=optional_team_id
NUXT_FIGMA_WEBHOOK_SECRET=your_webhook_secret

Running Locally

# Development server
npm run dev
# Visit http://localhost:3000

# Import from Figma
npm run figma:import

# Validate prompts
npm run validate:prompts

# Generate CSS/SCSS
npm run styles:build

📚 Documentation

Figma Integration Guide — Setup Figma API
CSS/SCSS Guide — Generate styles
Validation Guide — Validate prompts
API Reference — API endpoints

🔗 API Endpoints

Prompts

GET /api/prompts — List all prompts
POST /api/prompts — Create prompt
GET /api/prompts/:id — Get prompt detail
PUT /api/prompts/:id — Update prompt
DELETE /api/prompts/:id — Delete prompt

Figma Integration

POST /api/figma/sync — Trigger sync from Figma
POST /api/figma/import — Import prompts
GET /api/figma/status — Check sync status

🔧 Scripts

Figma Operations

./scripts/figma_sync.sh import          # Import from Figma
./scripts/figma_sync.sh validate        # Validate prompts
./scripts/figma_sync.sh webhook-setup   # Setup webhook
./scripts/figma_sync.sh sync            # Watch mode

CSS Generation

./scripts/generate_styles.sh css        # Generate CSS
./scripts/generate_styles.sh scss       # Generate SCSS
./scripts/generate_styles.sh build      # Build + minify
./scripts/generate_styles.sh watch      # Watch mode

Validation

python3 scripts/validate_all.py prompts/
python3 scripts/schema_validator.py prompts/my-prompt.json
python3 scripts/figma_layer_validator.py figma_export.json

🌐 Deployment

Vercel

vercel link
vercel env add NUXT_FIGMA_API_TOKEN
vercel deploy

Docker

docker build -t hermes-prompt-hub .
docker run -p 3000:3000 \
  -e NUXT_FIGMA_API_TOKEN=... \
  -e NUXT_FIGMA_FILE_ID=... \
  hermes-prompt-hub

GitHub Actions

Auto-sync from Figma:

name: Sync Prompts

on:
  schedule:
    - cron: '0 * * * *'  # Hourly
  workflow_dispatch:

jobs:
  sync:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      - uses: actions/setup-python@v4
      - run: pip install requests
      - run: python3 scripts/figma_importer.py
      - run: git add prompts/ && git commit -m "🤖 Sync from Figma" || exit 0
      - run: git push

📊 Quality Metrics

Code Coverage: >85%
Bundle Size: ~200KB (gzipped)
Performance: Lighthouse >90
Accessibility: WCAG AA compliance

🤝 Contributing

Contributions welcome! See CONTRIBUTING.md

📝 License

🔗 Links

Built with ❤️ for prompt engineers and design systems teams

📋 Figma Layer Contract

The importer expects Figma PROMPT frames with the following layer structure:

PROMPT/example-v1
├── METADATA (group)
│   ├── title (text)
│   ├── description (text)
│   ├── category (text)
│   ├── strategy (text)
│   └── version (text)
├── CONTENT (group)
│   ├── system (text)
│   ├── user_template (text)
│   ├── guardrails (text)
│   └── output_format (text)
├── EXAMPLES (group)
│   └── example_N (frame)
│       ├── input (text)
│       ├── output (text)
│       └── explanation (text)
└── STRATEGY_CONFIG (group)
    ├── num_steps (text)
    └── step_structure (text)

Test Fixtures

Example test fixtures are available in evals/cases/:

figma_prompt_example_v1.json — Complete Figma PROMPT frame fixture

Use these fixtures to test the importer without real Figma data:

python3 scripts/figma_importer.py --fixture evals/cases/figma_prompt_example_v1.json

🤖 MCP Server Integration

Hermes includes a Model Context Protocol (MCP) server for integration with MCP clients like Claude Desktop, Cursor, and other AI assistants.

Available Tools

list_prompts — Enumerate all prompts in prompts/raw/
validate_prompt — Validate a specific prompt against schema
get_prompt_stats — Get collection statistics (strategies, categories, validity)

Quick Setup

# Copy config to Claude Desktop
mkdir -p ~/.config/Claude/
cp mcp/claude_desktop_config.json ~/.config/Claude/claude_desktop_config.json

# Edit config with absolute path to your installation
# Restart Claude Desktop

Usage

# Test from CLI
python3 mcp/server.py list
python3 mcp/server.py validate --filename prompt-1.json
python3 mcp/server.py stats

# In Claude Desktop: "List my prompts" or "Validate prompt-1.json"

See mcp/README.md for detailed documentation.

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained

ResponsivenessSlow

Resources

Related MCP Connectors

PromptOTOAuth
com.promptot
Manage, version, and publish LLM prompts with blocks, variables, and evaluations.
Developer Tools AI & Machine Learning RAG Systems
2
https://mcp.promptot.com/mcp
Prompt Maker StudioOAuth
io.github.chrysogonus
Your prompt library in any MCP client: list, fetch, save and version prompt templates.
AI & Machine Learning Developer Tools
15
https://neadlab.com/api/mcp
Figma MCP ServerOAuth
com.figma.mcp
The Figma MCP server brings Figma design context directly into your AI workflow.
Developer Tools Content Management Systems
32,129
https://mcp.figma.com/mcp
SupernovaOAuth
io.supernova
Access and maintain design system docs, tokens, components, skills, and contexts across any project.
Design Tools Documentation Access Developer Tools
1
https://mcp.supernova.io/mcp

Related MCP Servers

Figma MCP Server
Developer Tools App Automation Content Management Systems
TimHolden
A
license
B
quality
D
maintenance
Enables seamless interaction with Figma via the Model Context Protocol, allowing LLM applications to access, manipulate, and track Figma files, components, and variables.
Updated 2 years ago (2025-03-09 06:51 UTC)
2
949 npm
149
MIT
Figma MCP Server
Developer Tools App Automation
MatthewDailey
F
license
B
quality
D
maintenance
Enables AI assistants to interact with Figma files through the ModelContextProtocol, allowing viewing, commenting, and analyzing Figma designs directly in chat interfaces.
Updated a year ago (2025-05-29 22:16 UTC)
5
3,051 npm
213
-
Handle Figma MCP
Design Tools Developer Tools
GEON1999
A
license
B
quality
D
maintenance
Enables AI assistants to read and modify Figma designs programmatically through the Model Context Protocol.
Updated 5 months ago (2026-05-19 05:22 UTC)
48
7 npm
1
MIT
Devign MCP
Design Tools Autonomous Agents
SodiqOgundairo
F
license
Not graded
quality
D
maintenance
Enables any AI model to create, read, and edit Figma designs in real time through the Model Context Protocol.
Updated 7 months ago (2026-03-31 11:10 UTC)
-