
Vistoya
β Officialfrom exa-labs
Google for agentic fashion shopping/discovery. Indexed fashion brand e-coms. Semantic search.
Vistoya MCP
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 - all over a single Streamable HTTP connection.
What is MCP?
The Model Context Protocol is an open standard that lets AI applications connect to external data sources and tools. Instead of building custom integrations for every AI platform, you expose a single MCP server and any compatible agent can use it.
Vistoya's MCP server exposes 6 read-only tools that cover the full product discovery workflow:
Tool Purpose discover_products Natural language semantic search with AI embeddings find_similar_products "More like this" recommendations discover_brands Natural language brand discovery find_similar_brands Find brands similar to a known brand get_product Full product details by ID get_filters Available filter values and price range
Endpoint
https://api.vistoya.com/mcp
The server uses Streamable HTTP transport - the current MCP standard for remote servers. No WebSocket upgrade required.
Key features
-
Semantic search - agents can query with natural descriptions like "oversized wool coat" or "linen shirt for a beach wedding under $200"
-
Rich taxonomy - every product is AI-classified with category, subcategory, colors, materials, gender, occasion, season, style, fit, and silhouette
-
Stateful sessions - the server maintains sessions via the
mcp-session-idheader with a 30-minute idle timeout
Next
Continue to Getting Started to copy the system prompt and connect the server to Claude Desktop, Cursor, or any MCP-compatible client.
This tool doesn't publish a standard install command β the repository README on GitHub covers its setup.
No common issues documented yet. If you hit a problem, the repository's GitHub Issues page is the best place to look.