Log inSubmit server
Market logo

Market

Searches Vistoya’s multi-store fashion index and returns product, brand, and similarity recommendations through MCP.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Market

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "market": {
      "command": "npx",
      "args": [
        "-y",
        "@vistoya/mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y @vistoya/mcp

Process exited before answering initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 3d ago.

Overview

Searches Vistoya’s multi-store fashion index through the market MCP server, using natural-language queries, filters, and product or brand similarity tools. It connects AI agents to Vistoya’s Streamable HTTP endpoint at https://api.vistoya.com/mcp. The indexed catalog uses vision-language embeddings to support semantic product and brand discovery. Reach for it when an agent needs to find fashion items, compare styles, inspect product details, or explore brands across multiple stores.

Use cases

  • Find fashion products across multiple stores using natural-language requirements
  • Compare products similar to a known item
  • Discover brands by style, origin, or aesthetic
  • Retrieve product details for a recommendation workflow

Key features

  • Semantic product search with optional filters
  • Visual and semantic product similarity
  • Semantic brand discovery
  • Similar-brand recommendations
  • Product detail retrieval
  • Filter value discovery

Tools6

What Market lets your agent do. Expand a tool for its parameters.

Self-reported~178 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

7/7 checks healthy over the last 45d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 8d ago via OSV.dev · @vistoya/mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads31Package downloads in the last 30 days.
Last commit28d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Tools exposed6Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Market works

What the market MCP server does

The market MCP server connects MCP-compatible AI agents to Vistoya’s fashion marketplace index. Vistoya aggregates and indexes products from multiple stores, then represents catalog content with a vision-language model. Agents can search this index without relying only on exact product names or keywords.

Product discovery accepts a natural-language request such as a garment, color, style, gender, or price requirement. Optional filters narrow the results using values such as category, color, materials, brands, and other indexed attributes. Results are returned as ranked products, making the server suitable for conversational shopping or recommendation workflows.

Brand discovery is handled separately. An agent can search brand profiles by characteristics such as style, origin, or aesthetic, then request brands that resemble a known brand. Product-level similarity also supports finding visually and semantically related items from a supplied product ID.

How it works

The server uses Streamable HTTP and is available at https://api.vistoya.com/mcp. An MCP client sends tool calls to the remote endpoint, and the endpoint returns search results or requested catalog data. The public preview endpoint currently does not require authentication.

Semantic search is available for both products and brands. Product queries can combine free-text intent with optional constraints, while similarity requests use an existing product ID, brand name, or brand key as their starting point. get_filters lets an agent inspect the filter values available to the index before constructing a more constrained request.

Setup and configuration

The market MCP server can be started through the published npm package with:

Terminal
npx @vistoya/mcp

That command automatically detects and configures Claude Desktop, Claude Code, Cursor, Windsurf, and VS Code. Restart the client after setup.

For manual configuration, add the remote endpoint to the client’s MCP configuration. Claude Desktop and Claude Code use an mcpServers entry with the URL. Cursor uses the same structure in ~/.cursor/mcp.json. VS Code’s MCP configuration uses a servers entry with type set to http and the same URL.

Clients without remote MCP support can use mcp-remote as a stdio bridge. The repository does not document any required environment variables or authentication settings.

Tools and capabilities

The market MCP server exposes six tools:

  • discover_products searches indexed stores with natural language and optional filters, returning ranked products.
  • find_similar_products returns visually and semantically similar products for a product ID.
  • discover_brands searches brand profiles by style, origin, or aesthetic.
  • find_similar_brands finds brands related to a supplied brand name or key.
  • get_product retrieves full details for one product ID.
  • get_filters lists filter values such as categories, colors, materials, and brands.

Together, these tools support product recommendations, alternative-item discovery, brand research, and filter-aware shopping assistants.

Limitations and notes

The catalog is limited to products and brands indexed by Vistoya’s marketplace, so availability depends on that index. The project describes the service as a public preview. It also does not specify result schemas, update frequency, rate limits, or authentication requirements beyond stating that the current public endpoint requires no authentication.

The MIT license applies to the repository. Issues and feature requests are handled through the project’s GitHub repository.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Market

market is an MCP server that connects AI agents to Vistoya’s fashion marketplace index across multiple stores. Its main tools search products with natural-language queries and filters, find similar products, search and compare brands, retrieve product details, and list available filter values. It uses Vistoya’s Streamable HTTP endpoint.

Run `npx @vistoya/mcp` to install and configure it automatically for supported clients. The command detects Claude Desktop, Claude Code, Cursor, Windsurf, and VS Code; restart the client afterward. You can also add `https://api.vistoya.com/mcp` manually or use `mcp-remote` for clients without remote MCP support.

Yes, market works with Cursor through its remote Streamable HTTP endpoint. Add an `mcpServers` entry pointing to `https://api.vistoya.com/mcp` in `~/.cursor/mcp.json`, or run the automatic setup command and restart Cursor.

Yes, `discover_products` accepts natural-language searches with optional filters including color and price. The available filter values can be inspected with `get_filters`, which also lists categories, materials, brands, and other indexed options.

Related MCP servers

All in E-Commerce All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewMarket AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/market?style=directory)](https://allmcps.com/mcp/market)
HTML Embed
<a href="https://allmcps.com/mcp/market"><img src="https://allmcps.com/api/badge/market?style=directory" alt="Market on AllMCPs" /></a>