Tolstoy Shopper

Search products, view details, and try items on across stores powered by Tolstoy.

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
98%
Naming quality
93%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~668Tokens (tool definitions)
~1.0 KBTypical response size
Moderate attention impact (0.52% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "shopper": {
      "url": "https://apilb.gotolstoy.com/mcp/v1/shopper/mcp"
    }
  }
}

Remote endpoints

https://apilb.gotolstoy.com/mcp/v1/shopper/mcpstreamable-http

What it can do

Tool inventory

Tools (3)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢search_products(query, limit, cursor, filters)

Search the catalog by a specific free-text query (e.g. a product name, material, or occasion the shopper named). In marketplace mode, searches across every brand store on Tolstoy — one catalog, no store selection needed. Use this only when the shopper names something specific to look for. For open-ended browsing, featured, best sellers, or a collection, use browse_products instead. When shopping a single brand, the optional `filters` (category/productType/tag) narrow the results. Each result carries a `productRef`; pass it to get_product for full details.

Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "What the shopper is looking for."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 12,
      "description": "Maximum number of products to return."
    },
    "cursor": {
      "type": "string",
      "description": "Pagination cursor from a previous search result."
    },
    "filters": {
      "type": "object",
      "properties": {
        "category": {
          "type": "string",
          "description": "Restrict to a product category."
        },
        "productType": {
          "type": "string",
          "description": "Restrict to a product type."
        },
        "tag": {
          "type": "string",
          "description": "Restrict to products carrying this tag."
        }
      },
      "additionalProperties": false
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}
🟢get_product(productRef)

Load full details for one product by its `productRef` (from search_products or browse_products): description, price, media, the brand's real product videos, size guide, per-variant stock, and buy links. Returns each variant's id and options (size/color). Use it to resolve the exact `variantId` the shopper wants before calling build_cart, and to answer fit/sizing questions from the size guide. The response includes the product image so it can be seen directly.

Input Schema

{
  "type": "object",
  "properties": {
    "productRef": {
      "type": "string",
      "minLength": 1,
      "description": "Product reference token from search_products."
    }
  },
  "required": [
    "productRef"
  ],
  "additionalProperties": false
}
⚪try_on(productRef)

Opens an interactive virtual try-on for a product (by `productRef` from `search_products`): the shopper uploads their photo and gets a photorealistic image of themselves wearing the actual product — true to the real garment. Only available for brands that enabled marketplace try-on; when unavailable, the response says so and the product can still be viewed via its store link.

Input Schema

{
  "type": "object",
  "properties": {
    "productRef": {
      "type": "string",
      "minLength": 1,
      "description": "Product reference token from search_products."
    }
  },
  "required": [
    "productRef"
  ],
  "additionalProperties": false
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded3 tools
verifiedversion not recorded3 tools
verifiedversion not recorded3 tools