Snapsearch Mcp

Created By

shantanukumar222 months 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 Content Tools Comments

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.

Try in Playground

Server Config

{
  "mcpServers": {
    "snapsearch": {
      "command": "uvx",
      "args": [
        "snapsearch-mcp"
      ],
      "env": {
        "SCREENSHOTS_DIR": "/Users/yourname/Desktop",
        "OPENAI_API_KEY": "sk-..."
      }
    }
  }
}

Project Info

Created At

2 months ago

Updated At

2 months ago

Author Name

shantanukumar22

Star

Language

License

Recommend Servers

View All

Latvia Payments Mcp

@junter1989k-ai

11 days ago

Slovenia Payments Mcp

11 days ago

11 days ago

12 days ago

Language models generate; Concordance verifies. The verify tool checks a claim deterministically (no model in the loop) and returns HOLDS / BROKEN / INCOMPLETE with the worked reasoning and a sealed receipt (content_hash + cite_url) that re-fetches byte-identical or not at all. Also: ranked search over an ~11k-record library, seal_fetch to re-verify any receipt, redact to strip PII before text travels, and a sealed connection graph. Runs sovereign/offline too (stdlib-first Python). A public false-positive benchmark covers every domain: the engine has never sealed a falsehood. 38 tools live; remote endpoint at https://narrowhighway.com/mcp.

12 days ago

Tanzania Payments Mcp

@junter1989k-ai

11 days ago

Switzerland Payments Mcp

@junter1989k-ai

11 days ago

Slovakia Payments Mcp

@junter1989k-ai

11 days ago

PAPI

@getpapi

Persistent Adaptive Planning Intelligence - structured loop engineering for AI coding assistants, with memory that persists across sessions, tools, and teammates.

12 days ago

ContextBridge

@tijuthomas5

ContextBridge (CB) is a local-first retrieval layer that sits between your codebase and your AI coding agent. Instead of pasting raw source files into context or letting the AI guess which files matter, CB indexes your codebase's real structure (via Graphify) and returns a compact, ranked result — owner file, related files, key symbols, and dependency chains — grounded in your actual code. A typical response is ~4–8 KB instead of the 100+ KB of raw source an AI would otherwise need to read to answer the same question — roughly a 96% cut in input tokens sent to your cloud AI, with zero hallucinated file paths or method names.

12 days ago

11 days ago

11 days ago

11 days ago

11 days ago

Lithuania Payments Mcp

11 days ago

11 days ago

12 days ago

11 days ago

Portugal Payments Mcp

11 days ago

11 days ago

12 days ago

Zhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

a year ago

11 days ago

11 days ago

Pakistan Payments Mcp

@junter1989k-ai

11 days ago

Playwright Mcp

@microsoft