SnappShop MCP Server
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.
# š SnappShop MCP Server
A high-performance Model Context Protocol (MCP) server for SnappShop. This project allows LLMs (like Claude) to search for products, fetch detailed specifications, and browse categories from SnappShop in real-time.
š Key Features
Dual-Runtime Architecture:
Python Server: For local development and power users.
ArvanCloud Edge: A serverless, Iranian-edge implementation for global users and zero-latency access.
API-Driven: Replaced unreliable HTML scraping with a direct integration of the
apix.snappshop.irJSON API.Strict Normalization: Ensures identical data shapes between Python and JavaScript runtimes.
Currency Safety: Explicitly handles the Toman/Rial (1:10) conversion to prevent pricing errors.
Related MCP server: snapp-mcp
š Quick Test (Live Demo)
You can test the MCP protocol implementation directly via the ArvanCloud Edge deployment:
š Live Endpoint: https://snappshop.dr98mav-hhdrz.arvanedge.ir
Test it in your browser:
List Tools:
https://snappshop.dr98mav-hhdrz.arvanedge.ir/toolsNote: The
/callendpoint requires a JSON POST request to execute tools.
š What is MCP?
The Model Context Protocol (MCP) is an open standard that allows AI models to connect to external tools and data sources. Instead of the AI just "guessing" or using old training data, an MCP server gives the AI real-time capabilities.
How it works with SnappShop:
Claude realizes you want to find a product on SnappShop.
Claude sends a request to the MCP server:
"Call search_products with query='Samsung Galaxy'".The Server fetches live data from the API, normalizes it, and sends it back.
Claude reads the live data and gives you an accurate answer with real prices and links.
š ļø Deployment & Configuration
1. Local Python Server
Best for users with a local Python environment.
pip install -r requirements.txt
python server.py2. ArvanCloud Edge (Production)
Deploy worker/src/arvan_edge_mcp.js to ArvanCloud Edge. This is the recommended way for global users as it handles the Iranian network egress automatically.
āļø Claude Desktop Configuration
Add the following to your claude_desktop_config.json (usually located at %APPDATA%\Claude\claude_desktop_config.json on Windows).
Option A: Using Local Python (Direct)
{
"mcpServers": {
"snappshop-local": {
"command": "python",
"args": ["C:/path/to/snappshop-mcp/server.py"]
}
}
}Option B: Using the ArvanCloud Edge (via Inspector Bridge)
Since Claude Desktop expects a local process, we use the MCP Inspector to tunnel the remote Edge server into Claude.
{
"mcpServers": {
"snappshop-edge": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/inspector",
"https://snappshop.dr98mav-hhdrz.arvanedge.ir"
]
}
}
}š Project Structure
snappshop/: Python core logic.worker/: ArvanCloud Edge implementation.fixtures/: Live API samples for testing.contract.md: The shared data specification.
Developed for the MCP ecosystem. š
This server cannot be deployed
Maintenance
Related MCP Connectors
AI-agent product catalog: search, lookup & purchase routing over verified merchant data.
Live product discovery for AI shopping agents, with shopper-approved retailer handoff.
1Product search for AI agents: Amazon + Shopify, cart-to-checkout buy path. Pay-per-call, no API key.
Give AI assistants access to real-time data. Search the web, compare flights, find hotels, and more.
Related MCP Servers
- FlicenseCqualityBmaintenanceEnables AI clients to search, fetch and cross-compare products, prices, sellers, offers, availability and specifications between Digikala and SnappShop, with tools for finding the best price or best-value offer using explicit filters and explainable reasoning. It also supports remote Streamable HTTP deployment so the same capabilities can be registered as a custom connector in clients such as Grok.11-
- AlicenseAqualityAmaintenanceEnables AI agents to search Snappfood restaurants and SnappMarket stores across Iran, compare true order costs including packaging and delivery, read menus, minimum orders, ETAs and reviews, and surface live flash deals. All operations are read-only, with no login, basket, ordering or payment access.21395 PyPI37MIT
- AlicenseAqualityAmaintenanceEnables AI agents to search Digikala's catalogue, compare every seller's offers and prices, review ~30 days of price history, read customer reviews and Q&A, and surface current deals, all through read-only tools.23179 PyPI40MIT
- AlicenseAqualityAmaintenanceEnables AI agents to compare prices across Iranian online and in-person shops, inspect each seller's offer with warranty and installment details, review roughly a year of price history, score deals, and find the cheapest shop for a whole basket. It is read-only, requires no account or API key, and runs locally for Claude, Cursor or Copilot.26105 PyPI1MIT