Log inSubmit server
Visual Memory MCP logo

Visual Memory MCP

Caches local UI states with perceptual hashes and CLIP to reduce repeated vision-model analysis for coding agents.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Visual Memory MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "visual-memory-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@putervision/vision-memory-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y @putervision/vision-memory-mcp

initialize succeeded but no response to tools/list.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 12d ago.

Overview

Visual Memory MCP MCP server gives coding agents a local cache for screenshots, UI states, and visual transitions. It checks in-memory and perceptual-hash caches before using local CLIP search or a vision-LLM fallback, then stores redacted state data locally. Reach for it when agents repeatedly inspect interfaces, need element grounding, or must compare visual workflows and regression baselines. It runs as a Node.js stdio MCP server and also provides CLI commands for initialization, diagnostics, snapshots, video ingestion, and inspection.

Use cases

  • Cache repeated screenshot analysis during frontend coding
  • Search prior UI states by text or image similarity
  • Ground agent actions to CSS selectors and coordinates
  • Compare visual regression baselines with current states
  • Ingest E2E recordings into searchable visual timelines

Key features

  • Perceptual-hash and local CLIP visual retrieval
  • Screenshot analysis with accessibility-tree parsing
  • CSS-selector and coordinate element grounding
  • WebM and MP4 keyframe ingestion
  • Visual specifications and snapshot management
  • Local evidence packs and trajectory export

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

8/8 checks healthy over the last 59d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 4d ago via OSV.dev · @putervision/vision-memory-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars40Stargazers on the source repository.
npm downloads4.6kPackage downloads in the last 30 days.
Last commit28d agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Visual Memory MCP works

What the Visual Memory MCP MCP server does

Visual Memory MCP MCP server stores and retrieves visual UI state for AI coding assistants. It is intended for workflows where an agent repeatedly receives screenshots, screen recordings, or related interface states and would otherwise spend vision-model tokens reanalyzing them.

The server can analyze screenshots, search remembered states by text or image similarity, identify likely interface elements, and retain transitions between states. It also supports visual specification baselines, named snapshots, state comparison, video-derived timelines, and deletion of stored states. The repository describes local LanceDB storage, local CLIP embeddings, perceptual hashing, and PII redaction as part of its local-first design.

How it works

Visual Memory MCP MCP server uses a four-stage lookup path. It first checks an in-memory cache, then scans perceptual hashes, then searches local CLIP vectors. If those checks miss, the architecture falls back to a vision LLM, ingests the resulting state, and saves it for later retrieval. Cached results can include descriptions and grounded interface elements.

The server represents UI changes as state transitions. Agents can record action outcomes, find navigation paths, wait for a target visual state, and compare layouts or recorded trajectories. WebM and MP4 recordings can be converted into searchable keyframe timelines.

Setup and configuration

Node.js 18.18.0 or newer is required. Install the package globally with npm, run vision-memory-mcp init --yes from a project root, and add a stdio entry that invokes vision-memory-mcp run to the MCP client configuration. Initialization scaffolds database directories, a .gitignore, .env, and IDE rules.

Use vision-memory-mcp run --skip-model-load when heavy CLIP model downloads should be skipped, such as in an offline or air-gapped environment. The CLI also includes doctor and doctor-global checks, plus commands for inspecting stored states, registering visual specifications, saving snapshots, ingesting recordings, and opening the graph viewer.

Tools and capabilities

The 15 consolidated MCP tools cover these areas:

  • Screenshot analysis with perceptual hashing and accessibility-tree parsing.
  • Text and image semantic retrieval through recall_memory.
  • Session summaries, cache metrics, and compact context export.
  • CSS-selector and coordinate prediction for element grounding.
  • Action outcomes, blockers, navigation paths, and visual-state polling.
  • Video ingestion, timeline search, state comparison, and trajectory export.
  • Visual specification contracts, snapshots, state undo, and privacy-focused state deletion.
  • Evidence-pack creation for linking visual records to task-memory data.

Visual Memory MCP MCP server is therefore a fit for frontend agents, end-to-end test recordings, visual regression checks, and workflows that need compact visual context rather than repeated full image analysis.

Limitations and notes

Its standard configuration uses a local stdio process, local vector storage, and local CLIP processing. Skipping model loading changes availability of the CLIP stage and may affect retrieval behavior.

The README names Cursor, Claude Code, Gemini, Copilot, Claude Desktop, Antigravity, Windsurf, Zed, and Roo Code in its integration material. Only clients supported by the directory schema can be represented in the listing metadata.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Visual Memory MCP

Visual Memory MCP is an MCP server that connects AI coding assistants to a local cache of screenshots, UI states, and visual transitions. Its main tools analyze screenshots, recall states by text or image, ground elements to selectors and coordinates, ingest video, compare states, manage visual specs and snapshots, and create evidence packs.

Install it globally with npm using `npm install -g @putervision/vision-memory-mcp`, then run `vision-memory-mcp init --yes` in the project root. Add a stdio MCP configuration that runs `vision-memory-mcp run`. Node.js 18.18.0 or newer is required.

Yes, the README names Cursor as a supported coding assistant. Add a `vision-memory-mcp` entry to Cursor's MCP configuration, such as `.cursor/mcp.json`, with `vision-memory-mcp` as the command and `run` as its argument.

Yes, it can ingest WebM and MP4 recordings into visual state timelines. The CLI example uses `vision-memory-mcp video ingest` with a recording path and category, while the `manage_video` MCP tool handles video memory and timeline search.

Related MCP servers

All in Knowledge & Memory All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewVisual Memory MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/visual-memory-mcp?style=directory)](https://allmcps.com/mcp/visual-memory-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/visual-memory-mcp"><img src="https://allmcps.com/api/badge/visual-memory-mcp?style=directory" alt="Visual Memory MCP on AllMCPs" /></a>