PixelForge MCP
An MCP server for AI-powered image generation, editing, analysis, and transformation using Google's Gemini and Imagen 4 models.
Features
- 21 MCP tools for image generation, editing, analysis, transformation, and more
- 6 models including Gemini image models and Imagen 4 family
- Quality presets (fast/balanced/quality) for simplified model selection
- Parallel multi-image generation via asyncio.gather
- Image transforms — crop, resize, rotate, flip, blur, sharpen, grayscale, watermark
- Prompt template library — 24 curated templates across 10 categories
- Generation history — full audit trail with search and pagination
- Batch processing — generate up to 10 images in parallel
- Optional Vertex AI — upscaling (x2/x4) and advanced editing modes
- Thinking mode & grounding — extended reasoning and Google Search for analysis
- 14 aspect ratios (including panoramic) and temperature control
- Async-first architecture with full Pydantic validation
- EXIF metadata embedding (prompt, model, timestamp)
Quick Start
Requirements: Python 3.10+ and a Google API key
Install
pipx install pixelforge-mcp
Configure
Claude Code
claude mcp add pixelforge --scope user -e GOOGLE_API_KEY="your-key" -- pixelforge-mcp
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"pixelforge": {
"command": "pixelforge-mcp",
"env": {
"GOOGLE_API_KEY": "your-key"
}
}
}
}
VS Code
code --add-mcp '{"name":"pixelforge","command":"pixelforge-mcp","env":{"GOOGLE_API_KEY":"your-key"}}'
Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"pixelforge": {
"command": "pixelforge-mcp",
"env": {
"GOOGLE_API_KEY": "your-key"
}
}
}
}
Kiro
kiro-cli mcp add --name pixelforge --scope global --command pixelforge-mcp --env "GOOGLE_API_KEY=your-key"
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"pixelforge": {
"command": "pixelforge-mcp",
"env": {
"GOOGLE_API_KEY": "your-key"
}
}
}
}
Restart Claude Desktop after saving.
Use
Ask Claude to generate, edit, or analyze images — all 21 tools are available automatically.
Available Tools
Generation
| Tool | Description |
|---|---|
generate_image |
Generate images from text (6 models, 14 aspect ratios, quality presets, parallel multi-image) |
edit_image |
Modify existing images with text prompts |
remove_background |
Remove image background (transparent or white) |
transform_image |
Crop, resize, rotate, flip, blur, sharpen, grayscale, or watermark |
batch_generate |
Generate up to 10 images in parallel from multiple prompts |
Analysis
| Tool | Description |
|---|---|
analyze_image |
AI-powered image description with optional grounding |
extract_text |
OCR — extract text with confidence levels |
detect_objects |
Detect objects with bounding boxes |
compare_images |
Compare 2-10 images for differences |
Utility
| Tool | Description |
|---|---|
optimize_prompt |
Enhance prompts for better image generation (14 styles) |
estimate_cost |
Calculate generation costs per model/operation |
list_templates |
Browse 24 curated prompt templates across 10 categories |
apply_template |
Fill a template with your subject for a ready-to-use prompt |
list_available_models |
Model capabilities, speed, quality, and selection guidance |
get_server_info |
Server configuration and status |
History
| Tool | Description |
|---|---|
list_history |
Browse generation history with pagination and filtering |
get_generation_details |
Get full details of a specific generation |
Vertex AI (Optional)
| Tool | Description |
|---|---|
upscale_image |
Upscale images x2 or x4 (requires Vertex AI) |
advanced_edit |
Inpainting, outpainting, background swap, style transfer (requires Vertex AI) |
Model Selection
PixelForge supports per-request model switching with 6 models:
Gemini Models (via Gemini API)
| Use case | Model | Why |
|---|---|---|
| Fast iterations | gemini-2.5-flash-image (default) |
Cheapest, lowest latency |
| Panoramic & grounded | gemini-3.1-flash-image-preview |
1:4/4:1/1:8/8:1, web+image grounding |
| Max text fidelity | gemini-3-pro-image-preview |
~94% accuracy, complex multi-turn edits |
Imagen 4 Models (via Gemini API)
| Use case | Model | Why |
|---|---|---|
| Cost-effective batch | imagen-4.0-generate-001 |
$0.04/img, excellent quality |
| Cheapest generation | imagen-4.0-fast-generate-001 |
$0.02/img, fastest |
| Maximum quality | imagen-4.0-ultra-generate-001 |
$0.06/img, best output |
Quality Presets
Instead of choosing a model manually, use quality presets:
generate_image(prompt="...", quality="fast") # gemini-2.5-flash-image
generate_image(prompt="...", quality="balanced") # gemini-3.1-flash-image-preview + 1K
generate_image(prompt="...", quality="quality") # gemini-3-pro-image-preview + 2K
Vertex AI (Optional)
For advanced features like image upscaling and specialized editing modes:
- Set up a Google Cloud project with Vertex AI enabled
- Set the environment variable:
GOOGLE_CLOUD_PROJECT=your-project-id - Install the Vertex AI dependency:
pip install pixelforge-mcp[vertex]
PixelForge auto-detects Vertex AI credentials and unlocks upscale_image and advanced_edit tools.
Supported Aspect Ratios
| Ratio | Description |
|---|---|
1:1 |
Square (default) |
16:9 |
Widescreen landscape |
9:16 |
Mobile portrait |
2:3 |
Classic portrait |
3:2 |
Classic landscape |
3:4 |
Portrait |
4:3 |
Traditional landscape |
4:5 |
Instagram portrait |
5:4 |
Medium format |
21:9 |
Ultrawide |
1:4 |
Tall panoramic* |
4:1 |
Wide panoramic* |
1:8 |
Extra tall panoramic* |
8:1 |
Extra wide panoramic* |
* Panoramic ratios require gemini-3.1-flash-image-preview model
Troubleshooting
"Invalid API key" or "Authentication failed"
Double-check your Google API key is correct and has access to the Gemini API. Get a key at Google AI Studio.
"Command not found: pixelforge-mcp"
Ensure the pipx bin directory is in your PATH:
export PATH="$HOME/.local/bin:$PATH"
"Server not starting"
Check that pixelforge-mcp is installed:
pipx list | grep pixelforge
Vertex AI features not available
Ensure GOOGLE_CLOUD_PROJECT is set and google-cloud-aiplatform is installed:
pip install pixelforge-mcp[vertex]
Documentation
- Configuration Guide — detailed setup and environment options
- Changelog — version history
Contributing
See CONTRIBUTING.md for development setup, code standards, and pull request guidelines.
License
Acknowledgments
Built with FastMCP, Pydantic, and google-genai.
Author
Ahmed Al-Eryani @ Tehnolabs
PixelForge MCP - Forging pixels with AI
Metadata
Release files for pixelforge-mcp 0.5.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| pixelforge_mcp-0.5.4.tar.gz | 49.2 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| pixelforge_mcp-0.5.4-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 98.2 kB
Release files / pixelforge_mcp-0.5.4.tar.gz
| Download URL | pixelforge_mcp-0.5.4.tar.gz |
|---|---|
| Size | 49.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ee99f56a85187f7276dc7bff8db141657138def16bc021038238a65461114cc4
|
|
BLAKE2b-256 checksum How to use checksums |
cc839520725cd5eb826e48c6455482476a10ad3d8d37ad7a7eca1d50854933f6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Release files / pixelforge_mcp-0.5.4-py3-none-any.whl
| Download URL | pixelforge_mcp-0.5.4-py3-none-any.whl |
|---|---|
| Size | 49.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4a90a2e205b17b4db3ce917fd32c1eca49c226f63757f047b11069c7af92c9d8
|
|
BLAKE2b-256 checksum How to use checksums |
c3a2c9a47f746dd96930b8b4f0912c9badc145eb1949dd1b6b5c62adced03ad6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|