Pixel Surgeon
Connects Claude to Gemini, OpenAI, and Grok image generation APIs, plus Veo 3 for video. You get standard text-to-image and editing tools, but the interesting part is region repair: it can rerender specific tiles or cropped areas of an image to fix garbled text or corrupted regions, then composite them back with histogram matching. Includes style presets like neo-brutalist and retro-futurist infographic modes. Images save to a local directory with a browser viewer for managing output. Useful when you need to iterate on AI-generated images that have text rendering problems or need surgical fixes without regenerating the whole thing.
- GitHub stars
- 4
- tools
- 10
- auth
- Secret needed
- transport
- STDIO
- env vars
- 3
- last updated
- May 26, 2026
Tools
10 toolsPublic tool metadata for what this MCP can expose to an agent.
generate_imageText-to-image generation (single image)
Text-to-image generation (single image)
No parameter schema in public metadata yet.
generate_imagesParallel batch generation (1-8 images)
Parallel batch generation (1-8 images)
No parameter schema in public metadata yet.
generate_videoText-to-video via Veo 3 with audio (5s or 8s)
Text-to-video via Veo 3 with audio (5s or 8s)
No parameter schema in public metadata yet.
edit_imageEdit an existing image with natural language instructions
Edit an existing image with natural language instructions
No parameter schema in public metadata yet.
fix_imageGrid-based tile repair for garbled text (2x2, 3x3, etc.)
Grid-based tile repair for garbled text (2x2, 3x3, etc.)
No parameter schema in public metadata yet.
fix_regionTargeted region repair with automatic aspect ratio snapping
Targeted region repair with automatic aspect ratio snapping
No parameter schema in public metadata yet.
interactive_fixBrowser-based crop UI with multi-shot selection
Browser-based crop UI with multi-shot selection
No parameter schema in public metadata yet.
list_imagesList generated images and videos
List generated images and videos
No parameter schema in public metadata yet.
save_imageImport an external image into the workspace
Import an external image into the workspace
No parameter schema in public metadata yet.
remove_backgroundRemove image background (alpha channel transparency)
Remove image background (alpha channel transparency)
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
GOOGLE_API_KEYsecretGoogle AI API key (enables Gemini image/video generation)
OPENAI_API_KEYsecretOpenAI API key (enables GPT Image 1/2 generation)
XAI_API_KEYsecretxAI API key (enables Grok Imagine generation)
Readme
pixel-surgeon-mcp architecture
pixel-surgeon-mcp
MCP server for AI image & video generation, editing, and transplant-grade region repair
Powered by Gemini 3.1 Flash Image, OpenAI GPT Image 2, Grok Imagine, and Veo 3
Details
- Repository
- github.com/j-east/pixel-surgeon-mcp
- Categories
- AI & LLM Tools, Media & Entertainment
- Package
pixel-surgeon-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Lore Contextlore-context/lore-contextGoverned AI-agent memory, Evidence Ledger traces, evals, and portable context tools.4stars
Imagine Mcpn24q02m/imagine-mcpMCP server for image/video understanding & generation (Gemini/OpenAI/Grok)4stars
Acmi Mcpmadezmedia/acmiPersistent agent memory via ACMI — Profile/Signals/Timeline. 16 tools on Upstash Redis.3stars
Logic Serverauctalis/nocturnusaiAgent reasoning, memory, and token-optimized context for AI applications.2stars
Contextforge Mcpalfredoizdev/contextforge-mcpPersistent memory MCP server for Claude Code, Cursor, and GitHub Copilot.2stars