Skip to main content
MCP server CX Codex

Visual Memory MCP — Claude Code MCP server: features and setup

This server stores visual UI states and helps an agent find elements or compare screens. Use it to inspect interface changes and trace recorded tests.

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add vision-memory-mcp -- npx -y @putervision/vision-memory-mcp
Open on GitHub

What Visual Memory MCP does

Visual Memory MCP keeps interface states locally and searches for similar screens using perceptual hashes and local CLIP vectors. An agent can retrieve states from text or images, map interface elements to CSS selectors and coordinates, and trace transitions between screens.

The server processes WebM and MP4 recordings, extracts keyframes, and links them to state transitions. You can also register a screenshot or mockup as a baseline for visual regression checks and save state snapshots. Node.js 18.18.0 or later is required. A startup option skips the CLIP model download, but semantic search relies on that model.

What it helps with

  • find a saved screen from an image or description
  • map an interface element to a CSS selector and coordinates
  • trace screen changes in a WebM or MP4 recording
  • compare the UI against a registered mockup
  • save and restore a visual state snapshot

Example prompts for the agent

  • Find a saved state that resembles this screenshot with recall_memory.
  • Locate the button and return its selector and coordinates using predict_next_action.
  • Analyze ./playwright-test.webm and trace the screen transitions.

How to install Visual Memory MCP

Platform CLI

claude mcp add vision-memory-mcp -- npx -y @putervision/vision-memory-mcp

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about Visual Memory MCP

How do I install Visual Memory MCP in Claude Code?

Run claude mcp add vision-memory-mcp -- npx -y @putervision/vision-memory-mcp. It requires Node.js 18.18.0 or later.

What does Visual Memory MCP do?

It stores UI states locally, retrieves similar screens, and helps an agent identify interface elements. It can also process video recordings and compare screens with a visual baseline.

Does Visual Memory MCP need the CLIP model?

You can start the server with --skip-model-load to bypass downloading the model. Semantic retrieval uses local CLIP vectors, so that feature depends on the model.

Similar MCP servers

All MCP servers for Agent setup: memory, context, orchestration →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor