screen-memory-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
π§ Screen Memory MCP
Give Claude a perfect memory of everything that's ever been on your screen.
"What was I researching on ChatGPT an hour ago?" "What code did I write this morning?" "Walk me through what I did in the last 30 minutes."
Just ask Claude. It remembers.
How it works
Every N seconds:
πΈ Screenshot β π€ Windows OCR β 𧬠Embed β πΎ SQLite
(built-in, accurate, (local model, (text only,
no hallucination) no API calls) ~5KB/capture)100% local. No images stored. No cloud. No API costs.
Related MCP server: Screen Vision MCP Server
Features
Semantic search β "find when I was reading about X" across your entire screen history
Activity timeline β connected narrative of what you did and why, not just isolated snapshots
Code tracking β detects VS Code / PyCharm, tracks which files you edited, computes diffs between captures
App awareness β knows if you were in a browser, editor, or terminal and tags captures accordingly
Tiny footprint β text + embeddings only, ~5KB per capture, ~30MB/day at 10s interval
Requirements
Windows 10 / 11
Python 3.11+
No Tesseract. No cloud APIs. No external accounts.
Installation
git clone https://github.com/YOUR_USERNAME/screen-memory-mcp
cd screen-memory-mcp
pip install -r requirements.txtUsage
1. Start the capture daemon
python -m screen_memory.capture --interval 10Interval | Storage/day | Recommended for |
5s | ~90MB | Maximum detail |
10s | ~45MB | Daily use β |
30s | ~15MB | Light use |
2. Connect to Claude Desktop
Edit %APPDATA%\Claude\claude_desktop_config.json:
{
"mcpServers": {
"screen-memory": {
"command": "C:\\Python314\\python.exe",
"args": ["-m", "screen_memory.server"],
"cwd": "C:\\path\\to\\screen-memory-mcp",
"env": {
"PYTHONPATH": "C:\\path\\to\\screen-memory-mcp"
}
}
}
}Restart Claude Desktop. The screen-memory tools will appear automatically.
3. Ask Claude anything
"What was I doing 20 minutes ago?"
"Summarize my activity for the last hour"
"What code did I write today in VS Code?"
"Find when I was reading about async Python"
"How did server.py change during my coding session?"MCP Tools
Tool | Description |
| Semantic search across all captures |
| Chronological narrative of a time range |
| Code diffs per file for a coding session |
| Latest N captures |
| Full text of a specific capture by ID |
| DB size, capture count, date range |
Auto-start on login (Windows)
Run once in an elevated terminal:
schtasks /create /tn "ScreenMemoryCapture" /tr "C:\path\to\start_capture.bat" /sc onlogon /ru YOUR_USERNAME /fStorage
All data lives in ~/.screen_memory/memory.db β a single SQLite file.
To wipe everything: just delete it.
Privacy
β Fully offline after install
β No screenshots saved to disk
β All text stays on your machine
β Open source β every line auditable
β Delete anytime:
rm -rf ~/.screen_memory
Roadmap
macOS / Linux support
Auto-cleanup (configurable retention period)
System tray app (start/stop without terminal)
Screenshot viewer (opt-in)
Multi-monitor support
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
Related MCP Connectors
Long-term memory for Claude, ChatGPT, Cursor: search, save and organize notes, links, docs, videos.
Memory for your AI: what you saw on screen, said in calls and worked on, searchable by agents.
Your own memory inside ChatGPT and Claude, with the source of every note.
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
Related MCP Servers
- AlicenseAqualityDmaintenancePersistent memory for Claude Code. Automatically indexes every conversation and provides production-grade hybrid search (BM25 + vectors + reranker) via MCP tools. 100% local, zero config, zero API keys, zero invoice.1650 npm8MIT
- FlicenseAqualityDmaintenanceEnables Claude to capture screenshots, watch your screen in real-time, read text via OCR, and analyze video files, all running locally as an MCP server.14-
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to semantically search your entire local conversation history from Claude Desktop, ChatGPT and Claude Code, and to retrieve, browse, ingest and report on those conversations. All embeddings run locally, so no cloud, API keys, or data leave your machine.2MIT
- FlicenseNot gradedqualityBmaintenanceLets Claude answer questions about your own past computer activity by reading a local, AES-256-encrypted database of screenshots, OCR text, calendar events, conversations, and location traces in read-only mode. Queries like "What was I doing last Wednesday at noon?" are resolved entirely on your machine, with no network service or cloud involvement.-