daraz-mcp
Enables searching Daraz.pk products with smart cheapest detection and category support using documented API patterns.
README
Daraz MCP Server - Clean & Fast
A streamlined Model Context Protocol (MCP) server for searching Daraz.pk products. Built using documented Daraz API patterns for maximum reliability and performance.
⨠Features
- šÆ Simple & Clean: Just 2 tools instead of 6 confusing ones
- š” Official API Patterns: Uses documented
mods.listItemsstructure andajax=trueendpoints - šø Smart Cheapest Search: Auto-detects "cheapest" queries and searches extensively
- š« No Cache: Always fresh results, no .db files created
- š Multi-method: JSON API primary, Playwright browser fallback
- šØ Beautiful Output: Human-readable results with clickable links
- ā” Fast: Optimized using officially documented endpoints
š ļø Tools Available
1. search_daraz - The Main Search Tool
Smart search that handles everything automatically:
# Regular search
search_daraz("wireless mouse")
# Auto-detects cheapest requests
search_daraz("cheapest wireless mouse") # Searches 15 pages, sorts by price
# Explicit cheapest mode
search_daraz("mouse", cheapest=True)
# Price filtering
search_daraz("laptops", max_price=50000)
# Category search (uses documented category endpoints)
search_daraz("TV", category="televisions")
Features:
- Auto-detects "cheapest" in query and switches to extensive search mode
- Searches 15 pages for cheapest queries vs 5 for regular
- Sorts results by price for cheapest queries
- Returns formatted, clickable results
2. product_details - Get Product Info
product_details("https://www.daraz.pk/products/product-url")
š” API Implementation
This server uses officially documented Daraz.pk endpoints:
Search Endpoint
GET https://www.daraz.pk/catalog/
?ajax=true
&q=query
&page=1
&_keyori=ss
Category Endpoint
GET https://www.daraz.pk/{category}/
?ajax=true
&page=1
&q=search_within_category
Response Structure: data.mods.listItems[] contains product array
š Quick Setup
- Install dependencies:
pip install fastmcp requests beautifulsoup4 playwright
- Add to LM Studio
mcp.json:
{
"mcpServers": {
"daraz-search": {
"command": "C:\\path\\to\\python.exe",
"args": ["C:\\path\\to\\server_merged.py"]
}
}
}
- Test in LM Studio:
- "Find cheapest Nothing phone case"
- "Search for wireless mice under 2000 PKR"
- "Show me gaming laptops"
šÆ Improvements from Previous Version
Before (Confusing):
ā 6 different tools: search_daraz, search_daraz_structured, search_daraz_formatted, search_cheapest_daraz, search_most_expensive_daraz, product_details
ā Cache causing stale results
ā AI couldn't decide which tool to use
After (Clean):
ā
2 simple tools: search_daraz (smart), product_details
ā
No cache - always fresh results
ā
Auto-detection of user intent
ā
Uses documented API patterns
š Search Behavior
| Query Type | Pages Searched | Results | Sorting |
|---|---|---|---|
| Regular search | 5 pages | Up to 10 | As found |
| "Cheapest" query | 15 pages | 1 item | Price (lowest first) |
With cheapest=True |
15 pages | 1 item | Price (lowest first) |
With max_price |
5 pages | Filtered | As found |
š§ No Cache = Always Fresh
- ā
No
.dbfiles created - ā Every search hits Daraz API fresh
- ā Latest prices and stock status
- ā No stale cached results
š”ļø Anti-Bot Protection
- User-Agent rotation (5 different browsers)
- Random delays between requests (1.0-2.5s)
- Proper headers and referrers
- Graceful fallback to browser automation
š Usage Examples
For Users in LM Studio:
- "Find me the cheapest Nothing phone 1 case"
- "Search for wireless mice under 1500 PKR"
- "What are some good gaming laptops?"
- "Show me TVs in the television category"
For Developers:
# The AI will automatically choose the right parameters
search_daraz("cheapest phone cases") # cheapest=True, max_results=1
search_daraz("phone cases") # regular search, max_results=10
search_daraz("cases", max_price=500) # price filtering
š Ready to Use
This server is production-ready and uses officially documented Daraz.pk API patterns for maximum reliability. No seller account required - works with public endpoints only.
Start LM Studio, add the MCP server, and start shopping! šļø
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.