
Vision Squeezer
This server attacks the vision API billing problem most developers don't notice: LLMs charge by pixel dimensions, not file size, and every provider has different tiling math. It exposes tools to preprocess images before they hit Claude, GPT-4o, Gemini, or other vision models by cropping padding, snapping to tile boundaries, and simulating each provider's token calculation algorithm. The CLI supports auto mode for text detection, quality binary search to hit SSIM targets, and batch processing with JSON output. You'd reach for this when you're burning tokens on screenshots with solid borders or images that spill into extra tiles by a few pixels. Install via the interactive npx script, Claude Code plugin marketplace, or as a standalone Rust binary.
- GitHub stars
- 2
- tool
- 1
- transport
- STDIO
- last updated
- Oct 23, 2026
Tools
1 toolsPublic tool metadata for what this MCP can expose to an agent.
optimize_imageOptimizes an image to fit a vision-LLM token budget, returning the optimized image and a savings report.
Optimizes an image to fit a vision-LLM token budget, returning the optimized image and a savings report.
No parameter schema in public metadata yet.
Sponsors
Readme
VisionSqueezer Logo
VisionSqueezer
Fit images to a vision-LLM token budget before they reach the model. A library, CLI, and MCP server for code, agents, and pipelines.
Details
- Repository
- github.com/eralpozcan/vision-squeezer
- Categories
- AI & LLM Tools, Communication & Messaging
- Package
vision-squeezer- Transport
- STDIO
- Registry
- MCP registry, active