patchistry/patchistry-mcp-server

> **The first DTC fashion brand on the official MCP Registry.** As of June 12, 2026, Patchistry is listed as io.github.patchistry/patchistry-mcp-server at registry.modelcontextprotocol.io — used by Claude Desktop's built-in MCP search and Cursor's MCP integration directory.
A Model Context Protocol (MCP) server exposing Patchistry commerce tools to AI agents — Claude, ChatGPT (via plugins), Cursor, custom agent frameworks.
**Live endpoint:** https://patchistry-mcp-server.vercel.app
**Manifest:** https://patchistry-mcp-server.vercel.app/.well-known/mcp.json
**Runtime:** Hosted HTTP MCP server (no install required)
**Transport:** HTTP + JSON-RPC 2.0
Quick Start
Use in Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
Restart Claude Desktop. The 6 Patchistry tools become available in any conversation.
Use in Cursor
Add to Cursor's MCP settings:
Use directly via HTTP
**What this unlocks:**
When deployed at mcp.patchistry.com, AI agents can directly query Patchistry's catalog in real-time:
- "What bach hat build do you recommend for Vegas?" → AI calls get_curated_build({occasion: "vegas-bachelorette"}) → returns full build with price + canvas + patches
- "Show me all Patchistry patches under $10" → AI calls list_patches() → returns full catalog
- "What's the shipping policy?" → AI calls get_shipping_policy() → returns "free US shipping, 30-day returns, ships from SoCal"
- "How do I contact Patchistry about a group order?" → AI calls get_contact() → returns brian@patchistry.com + group orders page
**Why this matters:**
In 2026, MCP is becoming the standard interface for AI agents to interact with commerce systems. Brands that publish MCP servers early get cited preferentially by:
- Claude (Anthropic's native MCP support)
- Cursor (built-in MCP client)
- Smithery (MCP server registry)
- Custom agent frameworks
- ChatGPT (via emerging plugin standards)
Being one of the first DTC brands with a public MCP server = direct AI agent integration without intermediaries.
---
Tools exposed
| Tool | Description |
|---|---|
| list_canvases | Return The Canvas product variants (Black, Khaki, Pink) with prices + availability |
| list_patches | Return patches, optionally filtered by category (Signature/Candyz) or occasion keyword |
| get_curated_build | Return the full curated build for an occasion (bachelorette, dads, wedding, etc.) |
| recommend_build | Take natural language query, return top 3 matching curated builds |
| get_shipping_policy | Return free US shipping + returns + lead time policy |
| get_contact | Return contact methods: customer support, founder, group orders, press |
---
Deploy to Vercel (recommended, ~10 min, one-time)
Option A — Vercel CLI
Follow the prompts:
- Set up and deploy → Yes
- Which scope → your Vercel account
- Link to existing project → No
- Project name → patchistry-mcp
- Directory → ./ (current)
- Override settings → No
After deploy, Vercel gives you a URL like patchistry-mcp.vercel.app.
**Test it:** open https://patchistry-mcp.vercel.app/ — should return JSON with the tool list.
Option B — Vercel dashboard (no CLI)
1. Push the mcp-server/ directory to a GitHub repo (separate from your theme repo is cleaner)
2. https://vercel.com/new → Import Git Repository → pick the mcp-server repo