Skip to main content
Glama

Klydo MCP Server

CI PyPI version Python 3.11+ License: MIT MCP Compatible

Fashion discovery MCP server for Indian Gen Z.

Enables AI assistants like Claude to search and discover fashion products from Klydo โ€” India's Gen-Z quick tech fashion commerce platform based in Bangalore.

โœจ Features

  • ๐Ÿ” Search Products โ€” Search fashion items with filters (category, gender, price range)

  • ๐Ÿ“ฆ Product Details โ€” Get complete product info including images, sizes, colors, ratings

  • ๐Ÿ”ฅ Trending Products โ€” Discover what's popular right now

  • ๐Ÿ“ Structured Logging โ€” Debug-friendly logs with Loguru

  • โšก Fast & Cached โ€” In-memory caching for quick responses

Related MCP server: Vistoya

๐Ÿš€ Quick Start

Installation

# Using pip
pip install klydo-mcp

# Or using pipx (isolated environment)
pipx install klydo-mcp

# Or using uvx (no installation needed)
uvx --from klydo-mcp klydo

Option 2: Install from Source

# Clone the repository
git clone https://github.com/myselfshravan/klydo-mcp.git
cd klydo-mcp

# Install dependencies with uv
uv sync

Usage with Claude Desktop

If installed via PyPI (pip/pipx)

Add to your Claude Desktop configuration:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "klydo": {
      "command": "klydo"
    }
  }
}
{
  "mcpServers": {
    "klydo": {
      "command": "uvx",
      "args": ["--from", "klydo-mcp", "klydo"]
    }
  }
}

If installed from source

{
  "mcpServers": {
    "klydo": {
      "command": "uv",
      "args": ["--directory", "/path/to/klydo-mcp", "run", "klydo"]
    }
  }
}

Then restart Claude Desktop.

Run Standalone

uv run klydo

๐Ÿ› ๏ธ MCP Tools

search_products

Search for fashion products.

Parameter

Type

Description

query

string

required โ€” Search terms (e.g., "black dress", "nike shoes")

category

string

Filter by category (e.g., "dresses", "shoes")

gender

string

Filter by gender ("men" or "women")

min_price

int

Minimum price in INR

max_price

int

Maximum price in INR

limit

int

Max results (default 10, max 50)

get_product_details

Get complete product information.

Parameter

Type

Description

product_id

string

required โ€” Product ID from search results

Returns: Full details โ€” images, sizes, colors, ratings, and purchase link.

Discover what's hot rn ๐Ÿ”ฅ

Parameter

Type

Description

category

string

Category filter

limit

int

Max results (default 10, max 50)

โš™๏ธ Configuration

Copy .env.example to .env and customize:

# Request settings
KLYDO_REQUEST_TIMEOUT=30
KLYDO_CACHE_TTL=3600

# Debug mode (set to false in production)
KLYDO_DEBUG=false

# API token for klydo.in (required)
KLYDO_KLYDO_API_TOKEN=your-token

๐Ÿ“ Project Structure

klydo-mcp/
โ”œโ”€โ”€ src/klydo/
โ”‚   โ”œโ”€โ”€ __init__.py
โ”‚   โ”œโ”€โ”€ server.py          # MCP server entry point
โ”‚   โ”œโ”€โ”€ config.py          # Configuration (Pydantic Settings)
โ”‚   โ”œโ”€โ”€ logging.py         # Loguru configuration
โ”‚   โ”œโ”€โ”€ models/
โ”‚   โ”‚   โ””โ”€โ”€ product.py     # Product, Price models
โ”‚   โ””โ”€โ”€ scrapers/
โ”‚       โ”œโ”€โ”€ base.py        # Scraper protocol (interface)
โ”‚       โ”œโ”€โ”€ cache.py       # In-memory cache with TTL
โ”‚       โ””โ”€โ”€ klydo_store.py # Klydo.in API client
โ”œโ”€โ”€ tests/                 # Test suite
โ”œโ”€โ”€ .github/workflows/     # CI/CD pipelines
โ”œโ”€โ”€ pyproject.toml
โ””โ”€โ”€ README.md

๐Ÿงช Testing

# Run all tests
uv run pytest

# Run with verbose output
uv run pytest -v

# Run specific test file
uv run pytest tests/test_models.py

๐Ÿ”ง Development

# Install dev dependencies
uv sync --dev

# Run linting
uv run ruff check src/

# Format code
uv run ruff format src/

# Run the server locally
uv run klydo

๐Ÿค Contributing

We welcome contributions! Please see our Contributing Guide for details.

  1. Fork the repository

  2. Create a feature branch (git checkout -b feature/amazing-feature)

  3. Commit your changes (git commit -m 'Add amazing feature')

  4. Push to the branch (git push origin feature/amazing-feature)

  5. Open a Pull Request

๐Ÿ” Security

For security issues, please see our Security Policy.

๐Ÿ“„ License

MIT License โ€” see LICENSE for details.

๐Ÿข About Klydo

Klydo is a Bangalore-based startup building quick tech fashion commerce for Gen-Z (18-32 age group). We're making fashion discovery seamless, fast, and accessible. This MCP server extends our platform to AI assistants, enabling natural language fashion search.

Backed by innovation. Built for Gen-Z. Made in India. ๐Ÿ‡ฎ๐Ÿ‡ณ


Made with โค๏ธ in Bangalore, India

Available Tools

3 tools
get_product_detailsA

Get complete product information including all images, sizes, and specifications.

Args: product_id: The product ID from search results (the 'id' field)

Returns: Full product details with: - images: ALL product images from multiple angles (show all to users) - image_url: Primary product image - url: Buy link on klydo.in (may be null โ€” only show when present) - sizes, colors, description, specifications - Returns None if product not found.

Inputs: product_id (required). Returns: result

search_productsA

Search for fashion products on Klydo.

Args: query: Search terms (e.g., "black dress", "nike shoes", "cotton kurta") category: Filter by category (e.g., "dresses", "shoes", "tshirts", "kurtas") gender: Filter by gender ("men" or "women") min_price: Minimum price in INR (e.g., 500) max_price: Maximum price in INR (e.g., 2000) limit: Maximum number of results (default 10, max 50)

Returns: List of matching products. Each product has: - image_url: Direct CDN image link (always show this) - url: Buy link on klydo.in (may be null โ€” only show when present) - price, brand, name, category

Inputs: query (required), category, gender, min_price, +2 more. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelogโ€ฆ

    TDQS

    A4.2/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clear, distinct purpose: searching, getting trending products, and retrieving full product details. No overlap or ambiguity.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in snake_case (get_product_details, get_trending, search_products), making it easy to predict tool function.

    Tool Count5/5

    Three tools is appropriate for a focused fashion product server: search, trending, and details. No unnecessary bloat or missing essentials.

    Completeness4/5

    The set covers core operations (search, browse trending, view details). Minor gap: no explicit way to list categories or brands, but search and trending cover most use cases.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      The Vistoya MCP server gives AI agents direct access to a curated, multi-brand fashion catalog. Agents can search by structured filters, discover products through natural language, find similar items, and retrieve full product details โ€” all over a single Streamable HTTP connection.
      10 npm
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server that integrates multiple AI image generation providers (WaveSpeed, Nano Banana, OpenAI, Stability, fal.ai) to automate photoshoot tasks like product photography, fashion content, and batch editing.
      9
      MIT