Snapsearch Mcp

Created By
shantanukumar229 days ago
An AI agent + custom MCP server that sees your screenshots, understands what's in them, organizes them into clean folders, and lets you find anything with natural language. Fully local. No cloud uploads. No subscriptions.
Overview

🧠 snapsearch-mcp

Your screenshots folder is a disaster. snapsearch-mcp is a local-first AI-powered semantic search engine for screenshots on macOS/Windows . It uses vision models, embeddings, and vector search to understand screenshots, organize them automatically, and make them searchable using natural language.

✨ Features

  • 🔍 Semantic screenshot search
  • 🧠 GPT-4o Vision integration
  • 📂 Automatic organization into folders
  • 💾 Local ChromaDB vector storage
  • 🔒 Fully local workflow
  • ⚡ MCP-compatible for Claude Desktop
  • 🖥️ macOS optimized

🧩 Example

Search naturally:

find the react hooks error screenshot

Even if the filename is:

IMG_4829.png

snapsearch still finds it.


⚙️ How It Works

screenshot.png
GPT-4o Vision
Image understanding + OCR
text-embedding-3-small
ChromaDB vector storage
Natural language semantic retrieval


🔒 Privacy First

snapsearch runs entirely on your machine.

* screenshots never uploaded
* embeddings stored locally
* uses your own OpenAI API key
* no subscriptions
* no cloud backend


🧠 MCP Integration

Works with Claude Desktop through MCP.

Example config:

{
  "mcpServers": {
    "snapsearch": {
      "command": "snapsearch-mcp"
    }
  }
}


📦 Installation

pip install snapsearch-mcp


🚀 Vision

snapsearch is building toward an AI-native memory layer for your filesystem — where screenshots become searchable knowledge instead of forgotten clutter.

Server Config

{
  "mcpServers": {
    "snapsearch": {
      "command": "uvx",
      "args": [
        "snapsearch-mcp"
      ],
      "env": {
        "SCREENSHOTS_DIR": "/Users/yourname/Desktop",
        "OPENAI_API_KEY": "sk-..."
      }
    }
  }
}
Project Info
Created At
9 days ago
Updated At
9 days ago
Author Name
shantanukumar22
Star
-
Language
-
License
-
Category
Tags

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago