接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
npx -y @putervision/[email protected]Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add io.github.putervision-vision-memory-mcp -- npx -y @putervision/vision-memory-mcp@1.4.2在終端機中執行。
{ "mcpServers": { "io.github.putervision-vision-memory-mcp": { "command": "npx", "args": [ "-y", "@putervision/[email protected]" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令？ 兩種安裝方式的差異
@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.
🌐 Official Documentation & Website: visionmemorymcp.com
Prerequisites: Node.js >= 18.18.0
# Global installation via npm
npm install -g @putervision/vision-memory-mcp
Run init in your project root to scaffold database directories, .gitignore, .env, and IDE rules:
vision-memory-mcp init --yes
Add to your MCP client config (e.g. .cursor/mcp.json or .vscode/mcp.json):
{
"mcpServers": {
"vision-memory-mcp": {
"command": "vision-memory-mcp",
"args": ["run"]
}
}
}
# Run stdio MCP server directly via binary (after global install)
vision-memory-mcp run
# Start server skipping heavy CLIP model downloads (air-gapped / offline mode)
vision-memory-mcp run --skip-model-load
# Re-initialize across all registered workspace projects
vision-memory-mcp init-global
# Health check dependencies, sharp bindings, and git safety
vision-memory-mcp doctor
# Run health diagnostics & aggregate metrics across all registered projects
vision-memory-mcp doctor-global
# Inspect stored visual states and metadata in terminal ASCII table
vision-memory-mcp inspect
# Register baseline design mockup contract (Visual SDD)
vision-memory-mcp spec set --name "Dashboard" --file ./dashboard-spec.png
# Save visual memory checkpoint snapshot
vision-memory-mcp snapshot save --name "v1.0-milestone"
# Ingest WebM / MP4 video recording into visual state memory timeline
vision-memory-mcp video ingest ./playwright-test.webm --category playwright_test
# Open interactive force-directed visual graph viewer in browser
vision-memory-mcp view
compact_slice export for Pentad System 1 StatePack assembly.@putervision/state-memory-mcp task DAGs with visual state memory, generating cryptographically hashable evidence packs for compliance and audit trails.@putervision/vision-memory-mcp provides 15 production-grade consolidated MCP tools structured across 4 core visual perception & automation domains:
analyze_screenshot (L1/L2 perceptual dHash & AX tree parsing, single/batch), recall_memory (text & image semantic vector search), get_session_context (aggregated cache hit metrics, recent states, and sub-1KB compact_slice export).predict_next_action (deterministic CSS selectors & bounding coordinates), record_outcome (UI action transitions & visual blockers), get_navigation_paths (BFS shortest-path planner), wait_for_visual_state (polling for target UI state).manage_video (WebM/MP4 keyframe ingestion, timeline search), compare_states (visual layout diffs & video trajectory comparison), create_evidence_pack (cryptographic audit proof linking video keyframes to state-memory DAGs), export_trajectories (multimodal fine-tuning datasets).manage_visual_spec (mockup baseline contracts & regression checks), manage_snapshot (checkpoints, export, restore), undo_visual_mutation (revert state ingestion), forget_state (privacy & PII purging).👉 For complete parameter specifications, return schemas, and example payloads, see the Formal API Reference and Features & Architecture Guide.
Incoming Screen
│
▼
┌──────────────────────────────┐
│ L1: In-Memory Cache Lookup │ ──(Hit)──▶ Return Cached Description & Grounded Elements
└──────────────┬───────────────┘
│ (Miss)
▼
┌──────────────────────────────┐
│ L2: Perceptual Hash Scan │ ──(Hit)──▶ Return Cached Description & Grounded Elements
└──────────────┬───────────────┘
│ (Miss)
▼
┌──────────────────────────────┐
│ L3: Local CLIP Vector Search │ ──(Hit)──▶ Return Semantically Close
└──────────────┬───────────────┘
│ (Miss)
▼
┌──────────────────────────────┐
│ L4: Vision LLM Fallback │ ──(Ingest)──▶ Save Redacted State to DB
└──────────────┬───────────────┘
Explore dedicated guides and deep dives in the docs/ directory:
While vision-memory-mcp is designed for visual frontend state caching, UI testing, and multimodal workflows, it may not be appropriate for:
state-memory-mcp standalone instead).--skip-model-load for lightweight dHash-only perception if memory is constrained).# Run full unit and integration test suite across all 72 test files (312 tests)
npm run test
Developed and maintained by PuterVision. Released under the MIT License.
.vision-memory-mcp/. Zero telemetry or analytics data is ever transmitted.Local visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding.
{ "mcpServers": { "io.github.putervision-vision-memory-mcp": { "command": "npx", "args": [ "-y", "@putervision/[email protected]" ] } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式，而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Visual Memory MCP 透過 stdio 在本機執行。
上次檢查時間：2026-11-10。 Local visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding.