Vision Memory Mcp
Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead…
- Transport
- Not stated
- Package
- —
- Registry id
- —
No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.
Vision Memory MCP caches webpage and application UI screenshots locally to optimize context windows, accelerate execution speed, and eliminate redundant LLM vision costs. All screenshots, perceptual hashes, vector embeddings, and transition graphs are stored locally on the user's machine using embedded LanceDB, ensuring local-first privacy. It can match screenshots in less than 5ms using perceptual Difference Hashing (dhash), avoiding API calls.
It automatically scans workspace sub-directories, submodules, and sub-packages, federating multi-database visual memory queries across complex enterprise repositories. It provides 15 consolidated core MCP tools, including visual perception, navigation, video memory, spec compliance, and snapshot management tools.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.