FontLab MCP Server
Enables AI assistants to interact with FontLab for font design and manipulation, including querying font metadata, creating/modifying glyphs, applying transformations, and exporting fonts.
README
FontLab MCP Server
A Model Context Protocol (MCP) server that provides programmatic access to FontLab's PythonQt API, enabling Claude and other AI assistants to interact with FontLab for font design and manipulation.
Overview
This MCP server bridges the Model Context Protocol with FontLab's powerful font editing capabilities, allowing you to:
- Query font metadata and glyph information
- Create and modify glyphs programmatically
- Apply transformations (scale, rotate, translate)
- Export fonts to various formats
- Automate font design workflows
Architecture
┌─────────────────┐
│ Claude/MCP │
│ Client │
└────────┬────────┘
│ MCP Protocol (stdio)
│
┌────────▼────────┐
│ FontLab MCP │
│ Server │
│ (Python) │
└────────┬────────┘
│ Script Execution
│
┌────────▼────────┐
│ FontLab │
│ Application │
│ (PythonQt API) │
└─────────────────┘
The server uses a bridge pattern to execute Python scripts within FontLab's environment, communicating via temporary files and JSON serialization.
Features
Resources (Read-Only Operations)
fontlab://font/current- Get current font informationfontlab://font/current/glyphs- List all glyphsfontlab://font/info- Get detailed font metadatafontlab://glyph/{name}- Get specific glyph details
Tools (Write Operations)
create_glyph- Create new glyphs with custom parametersmodify_glyph_width- Adjust glyph widthstransform_glyph- Apply scale, rotation, and translationupdate_font_info- Modify font metadataexport_font- Export to OTF, TTF, WOFF, WOFF2, UFOdelete_glyph- Remove glyphs from font
Installation
Prerequisites
- Python 3.10 or higher
- FontLab 7 or 8 installed
pippackage manager
Setup
-
Clone this repository:
git clone https://github.com/dithilli/fontlab-mcp-server.git cd fontlab-mcp-server -
Create a virtual environment (recommended):
python3 -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate -
Install dependencies:
pip install -r requirements.txt -
Install the package:
pip install -e .
Configuration
The server automatically detects FontLab installations in standard locations:
- macOS:
/Applications/FontLab 8.appor/Applications/FontLab 7.app - Custom paths can be configured in the bridge initialization
Usage
Running the Server
Start the server using stdio transport:
python -m src.server
Or use the installed command:
fontlab-mcp-server
Claude Desktop Configuration
Add to your Claude Desktop config file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"fontlab": {
"command": "/path/to/venv/bin/python",
"args": ["-m", "src.server"],
"cwd": "/path/to/fontlab-mcp-server"
}
}
}
Example Usage with Claude
Once configured, you can ask Claude to:
Query font information:
"What fonts are currently open in FontLab?"
Create glyphs:
"Create a new glyph called 'customA' with a width of 650"
Modify glyphs:
"Scale the 'A' glyph by 1.2x horizontally"
Export fonts:
"Export the current font as an OTF to ~/Desktop/myfont.otf"
API Reference
Resources
Get Current Font
URI: fontlab://font/current
Returns: JSON with font metadata
List Glyphs
URI: fontlab://font/current/glyphs
Returns: Array of glyph objects with names, unicodes, and widths
Get Glyph Details
URI: fontlab://glyph/{name}
Parameters:
- name: Glyph name (e.g., "A", "space", "Agrave")
Returns: Detailed glyph information including bounds and contours
Tools
create_glyph
{
"name": "glyph_name",
"unicode": 65, // optional
"width": 600 // optional, default 600
}
modify_glyph_width
{
"name": "glyph_name",
"width": 650
}
transform_glyph
{
"name": "glyph_name",
"scale_x": 1.2, // optional, default 1.0
"scale_y": 1.0, // optional, default 1.0
"rotate": 45, // optional, default 0 (degrees)
"translate_x": 10, // optional, default 0
"translate_y": 0 // optional, default 0
}
update_font_info
{
"family_name": "My Font Family", // optional
"style_name": "Bold", // optional
"version": "1.0", // optional
"copyright": "Copyright 2025" // optional
}
export_font
{
"path": "/path/to/output.otf",
"format": "otf" // optional: otf, ttf, woff, woff2, ufo
}
delete_glyph
{
"name": "glyph_name"
}
Development
Project Structure
fontlab-mcp-server/
├── src/
│ ├── __init__.py # Package initialization
│ ├── server.py # Main MCP server
│ ├── fontlab_bridge.py # FontLab communication bridge
│ ├── resources.py # Resource handlers
│ ├── tools.py # Tool handlers
│ └── utils/ # Utility functions
├── scripts/ # FontLab executor scripts
├── tests/ # Unit tests
├── pyproject.toml # Package configuration
├── requirements.txt # Python dependencies
└── README.md # This file
Testing
Run tests:
pytest tests/
Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
Limitations & Notes
- FontLab must be running for the server to function
- Script execution uses subprocess communication, which may have latency
- Some FontLab features may require specific versions (7 or 8)
- The bridge assumes FontLab CLI accepts
-scriptflag (may need adjustment)
Roadmap
Future enhancements:
- [ ] Support for component manipulation
- [ ] Kerning table operations
- [ ] OpenType feature editing
- [ ] Batch glyph operations
- [ ] Real-time event streaming
- [ ] Better error handling and validation
- [ ] Support for multiple open fonts
- [ ] Undo/redo functionality
License
MIT License - See LICENSE file for details
Acknowledgments
- Built on Anthropic's Model Context Protocol
- Integrates with FontLab's Python API
Support
For issues, questions, or contributions, please visit:
- GitHub: https://github.com/dithilli/fontlab-mcp-server
- FontLab API Docs: https://fontlabcom.github.io/fontlab-python-docs/
Version: 0.1.0 Author: David Szarzynski Status: Alpha - MVP Implementation
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.