pinepaper/mcp-server

PinePaper MCP Server

Create animated graphics with AI using the Model Context Protocol

Overview

PinePaper MCP Server enables AI assistants to create and animate graphics in PinePaper Studio via the Model Context Protocol (MCP). Works with any AI that supports MCP tool calling (Claude, GPT, Gemini, local models, etc.). Using natural language, you can:

• Create text, shapes, and complex graphics
• Animate items with behavior-driven relations
• Generate procedural backgrounds
• Export animated SVG and training data

Quick Start

1. Install

# Using npm
npm install -g @pinepaper.studio/mcp-server

# Using bun
bun add -g @pinepaper.studio/mcp-server

2. Configure Your AI Client

Add to your MCP client configuration. Examples:

Claude Desktop (claude_desktop_config.json):

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "pinepaper": {
      "command": "npx",
      "args": ["-y", "@pinepaper.studio/mcp-server"]
    }
  }
}

Other MCP Clients: Refer to your AI client's MCP configuration documentation.

3. Start Using

Open your AI client and try:

"Create a red pulsing text that says HELLO"

"Create a sun and earth, make earth orbit the sun"

"Add a sunburst background with blue and purple colors"

Features

📐 Diagram Tools (NEW in v1.4.3)

Create flowcharts, UML diagrams, network diagrams, and more:

"Create a flowchart for user login process"
"Make a UML class diagram for the User class"
"Design a network topology with 3 servers connected to a cloud"

Shape Types:

• Flowchart: process, decision, terminal, data, document, database, preparation
• UML: uml-class, uml-usecase, uml-actor
• Network: cloud, server
• Basic: rectangle, circle, triangle, star

Connector Features:

• Smart routing (orthogonal, direct, curved)
• Arrow styles (classic, stealth, diamond, circle, none)
• Animated bolt effect for data flow
• Labels on connectors

Auto-Layout Algorithms:

• Hierarchical (flowcharts, org charts)
• Force-directed (network diagrams)
• Tree (hierarchies)
• Radial (mind maps)
• Grid (component libraries)

Tools:

• pinepaper_create_diagram_shape - Create diagram shapes with ports
• pinepaper_connect - Connect items with smart connectors
• pinepaper_connect_ports - Connect specific ports
• pinepaper_add_ports - Add connection ports to items
• pinepaper_auto_layout - Automatically arrange items
• pinepaper_get_diagram_shapes - List available shapes
• pinepaper_update_connector - Update connector properties
• pinepaper_remove_connector - Remove a connector
• pinepaper_diagram_mode - Control diagram editing mode

🔍 Asset Search & Import (NEW in v1.3.0)

Search and import free SVG assets from multiple repositories:

"Search for a rocket icon"
"Import a cat illustration"
"Add a user avatar icon"

Supported Repositories:

• SVGRepo: 500,000+ icons with various licenses
• OpenClipart: 150,000+ public domain clipart (CC0)
• Iconify: 200,000+ icons from multiple icon sets
• Font Awesome: 2,000+ free icons (CC BY 4.0)

Tools:

• pinepaper_search_assets - Search across all repositories
• pinepaper_import_asset - Import and place on canvas

📊 Performance Metrics (NEW in v1.3.0)

Built-in performance tracking helps AI assistants optimize workflows:

• Automatic timing for all tool operations
• Phase breakdown (validation, code generation, execution, screenshots)
• Export formats: summary, detailed JSON, CSV
• Self-optimization through pinepaper_get_performance_metrics

Example workflow:

1. Run your scene creation workflow
2. Call pinepaper_get_performance_metrics
3. Identify bottlenecks (e.g., individual creates vs batch)
4. Adjust approach and re-run

🐛 Enhanced Error Messages (NEW in v1.3.0)

Errors now include canvas context for easier debugging:

• Total item count and types
• Active relations
• Recent items created
• Canvas state at time of error

Makes troubleshooting much faster and more precise.

🎨 Item Creation

Create text, shapes, and custom graphics:

"Create a blue circle at position 200, 300 with radius 50"
"Add a gold star in the center"
"Create text saying 'Welcome' with font size 72"

🔄 Relations (Behavior-Driven Animation)

The key feature - describe HOW items should behave:

🎬 Simple Animations

For quick looping effects:

• pulse - Scale up/down
• rotate - Continuous spin
• bounce - Vertical bounce
• fade - Opacity cycle
• wobble - Side-to-side
• slide - Horizontal slide
• typewriter - Character reveal

🖼️ Background Generators

Procedural patterns:

• drawSunburst - Radial rays
• drawSunsetScene - Animated sunset
• drawGrid - Lines, dots, squares
• drawWaves - Layered waves
• drawCircuit - Tech circuit board

📊 Training Data Export

Generate instruction/code pairs for LLM fine-tuning:

"Export training data from this scene"

Outputs pairs like:

{
  "instruction": "moon orbits earth at radius 100",
  "code": "app.addRelation('item_1', 'item_2', 'orbits', {radius: 100})"
}

Tools Reference

Item Tools

Relation Tools

Animation Tools

Generator Tools

Effect Tools

Asset Tools (NEW)

Query Tools

Diagram Tools (NEW in v1.4.3)

Canvas Tools

Export Tools

Examples

Solar System

1. Create a yellow circle as the sun (radius 60) at center
2. Create a blue circle as Earth (radius 20)
3. Create a gray circle as the Moon (radius 8)
4. Add relation: Earth orbits Sun at radius 150, speed 0.3
5. Add relation: Moon orbits Earth at radius 40, speed 0.8

Animated Logo

1. Create text "BRAND" with font size 96
2. Apply pulse animation with speed 0.5
3. Apply sparkle effect with gold color
4. Add sunburst background

Following Labels

1. Create a circle as "player"
2. Create text "Player 1" as the label
3. Add relation: label follows player with offset [0, -50]

Flowchart Diagram (NEW)

1. Create a terminal shape with label "Start"
2. Create a process shape with label "Get Input"
3. Create a decision shape with label "Valid?"
4. Create a terminal shape with label "End"
5. Connect Start → Get Input
6. Connect Get Input → Valid?
7. Connect Valid? → End (label: "Yes")
8. Connect Valid? → Get Input (label: "No", routing: curved)
9. Apply hierarchical auto-layout

Network Diagram (NEW)

1. Create a cloud shape with label "Internet"
2. Create 3 server shapes with labels "Web", "API", "DB"
3. Connect Internet → Web (label: "HTTPS")
4. Connect Web → API (label: "REST")
5. Connect API → DB (label: "SQL")
6. Apply force-directed auto-layout

Architecture

┌─────────────────────────────────────────────────────────────┐
│                 AI Client (Claude, etc.)                    │
│                          │                                  │
│                    MCP Protocol                             │
│                          │                                  │
│              ┌───────────▼───────────┐                     │
│              │  PinePaper MCP Server │                     │
│              │  ┌─────────────────┐  │                     │
│              │  │  Tool Handlers  │  │                     │
│              │  └────────┬────────┘  │                     │
│              │           │           │                     │
│              │  ┌────────▼────────┐  │                     │
│              │  │ Code Generator  │  │                     │
│              │  └────────┬────────┘  │                     │
│              └───────────┼───────────┘                     │
│                          │                                  │
│              ┌───────────▼───────────┐                     │
│              │   PinePaper Studio    │                     │
│              │   (Browser/App)       │                     │
│              └───────────────────────┘                     │
└─────────────────────────────────────────────────────────────┘

Development

Setup

git clone https://github.com/pinepaper/mcp-server.git
cd mcp-server

# Using npm
npm install
npm run build

# Using bun (recommended)
bun install
bun run build

Test with MCP Client (Local)

1. Build the server:

   # Using npm
   npm run build
   
   # Using bun
   bun run build
   

2. Add to your MCP client config (example for Claude Desktop on macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):

   {
     "mcpServers": {
       "pinepaper": {
         "command": "node",
         "args": ["/full/path/to/mcp-server/dist/cli.js"]
       }
     }
   }
   

3. Restart your MCP client

4. Test with: "What PinePaper tools do you have available?"

Run Tests

# Using npm
npm test

# Using bun
bun test

# Run with coverage
bun test --coverage

Development Watch Mode

# Using npm
npm run dev

# Using bun
bun run dev

Internationalization (i18n)

PinePaper MCP Server supports 51 languages, providing localized tool descriptions and messages for AI agents.

Supported Languages

How It Works

The i18n system provides localized:

• Tool names and descriptions
• Error messages
• Success messages
• UI labels for item types, relations, animations, and generators

Setting Language

Set the PINEPAPER_LOCALE environment variable:

# In MCP client config (example for Claude Desktop)
{
  "mcpServers": {
    "pinepaper": {
      "command": "npx",
      "args": ["-y", "@pinepaper.studio/mcp-server"],
      "env": {
        "PINEPAPER_LOCALE": "ja"
      }
    }
  }
}

Or programmatically:

import { setLocale, t } from '@pinepaper.studio/mcp-server';

// Set locale
setLocale('fr');

// Get translated string
const description = t('tools.pinepaper_create_item.description');

Adding New Languages

1. Create a new locale file in src/i18n/locales/ (e.g., xx.ts)
2. Copy the structure from en.ts
3. Translate all strings
4. Export from src/i18n/locales/index.ts
5. Add to the localeMap

See for detailed guidelines.

Configuration

Environment Variables

Performance Metrics

PinePaper MCP Server includes built-in performance tracking to help AI assistants optimize workflows by identifying bottlenecks and choosing faster alternatives.

Key Features:

• ⚡ Automatic timing for all tool operations
• 📊 Phase breakdown (validation, code generation, browser execution, screenshots)
• 🎯 Real-time query via pinepaper_get_performance_metrics tool
• 📈 Export formats: summary, JSON, CSV
• 💾 In-memory storage (resets on restart)
• 🚀 Minimal overhead (~1ms per operation)

Quick Example:

AI: "Let me check if batch operations are faster"
→ pinepaper_get_performance_metrics(format: 'summary')

Result:
  - pinepaper_create_item: avg 145ms
  - pinepaper_batch_create (10 items): avg 298ms (~30ms per item)

AI: "I'll use batch_create for the next 20 items"

Configuration:

# Disable metrics if not needed
export PINEPAPER_METRICS_ENABLED=false

# Increase retention for long sessions
export PINEPAPER_METRICS_RETENTION=5000

Learn More: See for complete documentation.

Documentation

Guides

• - Decision trees, multi-step patterns, performance optimization, and troubleshooting
• - In-memory metrics system for AI self-optimization
• PinePaper Reference - Complete PinePaper Studio API reference

External Documentation

• PinePaper API Docs
• MCP Tools Specification

Contributing

We welcome contributions! Please see for guidelines.

Development Workflow

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Run tests: npm test
5. Submit a pull request

License

MIT License - see for details.

Links

• PinePaper Studio
• Documentation
• GitHub Issues
• MCP Specification

Support

• 📧 Email: support@pinepaper.studio
• 🐛 Issues: GitHub Issues

Made with ❤️ by the PinePaper team