Vision MCP Server

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent

Local serverstdio

What is the Vision MCP Server?

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and

What the server does

@putervision/vision-memory-mcp is a zero-infrastructure, local-first Model Context Protocol (MCP) server and CLI tool that provides AI coding assistants (such as Cursor, Claude Code, Gemini, or Copilot) with visual state caching using perceptual hashing, local CLIP embeddings, and transition graphs to eliminate repetitive vision LLM calls.

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

How to install the Vision MCP Server

{
  "mcpServers": {
    "vision-memory-mcp": {
      "command": "vision-memory-mcp",
      "args": [
        "run"
      ]
    }
  }
}

From the project documentation. Replace placeholders and example paths before connecting.

Frequently asked questions

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.