Patchistry MCP Server
Overview
Description from the maker (original English)
DTC modular hat brand MCP server. 6 tools for AI agents: catalog, curated builds, shipping.
PopNx MCP’s three pillars
These three are never merged into one score: opinions, measurements and popularity are different things.
- User voiceiNo reviews yetReviews open together with accounts in a later step
- Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
- UsageiVery new↓ 61/wk · ★ –
What you can do with it
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
- Connection: Computer or cloud
- Transport: stdio, Streamable HTTP
- Category: Marketing & social media
Install
Pick the AI app you use, then copy the settings.
Before you install
- Basic checks: 1 of 1 passed
- Runs on the maker’s server: what you ask it goes through their server.
- The registry lists no key to fill in.
You need
- Runs in the cloudNothing to install; it connects over the internet
- npmNode.js installed (for the npx command)
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
- Open Settings → Connectors
- Press Add custom connector
- Paste the address below and press Add
- If it asks you to sign in, sign in with the maker
https://patchistry-mcp-server.vercel.app/rpcOr run it on your computer
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"patchistry": {
"command": "npx",
"args": [
"-y",
"patchistry-mcp-server"
]
}
}
}Run this in your terminal
claude mcp add --transport http patchistry https://patchistry-mcp-server.vercel.app/rpcOr run it on your computer
claude mcp add patchistry -- npx -y patchistry-mcp-serverOr copy the settings yourself
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"patchistry": {
"url": "https://patchistry-mcp-server.vercel.app/rpc"
}
}
}Or run it on your computer
Or copy the settings yourself
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"patchistry": {
"command": "npx",
"args": [
"-y",
"patchistry-mcp-server"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Or copy the settings yourself
Paste into .vscode/mcp.json in your project
{
"servers": {
"patchistry": {
"type": "http",
"url": "https://patchistry-mcp-server.vercel.app/rpc"
}
}
}Or run it on your computer
Or copy the settings yourself
Paste into .vscode/mcp.json in your project
{
"servers": {
"patchistry": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"patchistry-mcp-server"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
- Open ChatGPT on the web → Settings → Connectors (Apps)
- Press Create or Add (some plans need Developer mode under Advanced first)
- Paste the address below, give it a name and save
- If it asks you to sign in, sign in with the maker
https://patchistry-mcp-server.vercel.app/rpcMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
What it can do
We have not read this server’s tool list yet; we check endpoints in rotation.
Basic checksi
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 9, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account patchistry, which owns the repo
- … Not checked yet
Still maintained
We have not read this repo from GitHub yet
- … Not checked yet
Has a licence
We have not read this repo from GitHub yet
- … Not checked yet
Endpoint responds
Not checked yet; we check endpoints in rotation
- … Not checked yet
Sign-in with OAuth
Not checked yet; we check endpoints in rotation
- … Not checked yet
No hidden instructions in tool descriptions
Not checked yet; we read the tool list when we check the endpoint
Compared with others in Marketing & social mediai
- More stars than 0% of the other 3630 servers in this category
- Published to the registry more recently than 12% of the other 3630 servers in this category
- Basic checks equal to or better than 100% of the other 3630 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is Patchistry MCP Server safe?
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
What keys or codes does it need?
The registry does not list a required key, though some servers ask you to sign in on first use.
Does it run on my computer or in the cloud?
Either way works: install it on your computer or connect to the cloud version.
Is it still maintained?
The GitHub repo last changed –, and the latest version (0.2.0) reached the registry 5 months ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
What can I use instead?
In the same category: MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
Alternatives
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Google Analytics MCP
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
BibiGPT YouTube Video Summarizer
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
README from the maker
Open the README
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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-serverat 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):
{
"mcpServers": { "patchistry": { "command": "npx", "args": ["mcp-remote", "https://patchistry-mcp-server.vercel.app/rpc"] } } }
Restart Claude Desktop. The 6 Patchistry tools become available in any conversation.
Use in Cursor
Add to Cursor's MCP settings:
{
"mcpServers": { "patchistry": { "url": "https://patchistry-mcp-server.vercel.app/rpc" } } }
Use directly via HTTP
# List tools
curl https://patchistry-mcp-server.vercel.app/tools
Call a tool (REST)
curl -X POST https://patchistry-mcp-server.vercel.app/tools/get_curated_build \ -H "Content-Type: application/json" \ -d '{"occasion":"bachelorette"}'
Call a tool (JSON-RPC)
curl -X POST https://patchistry-mcp-server.vercel.app/rpc \ -H "Content-Type: application/json" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"recommend_build","arguments":{"query":"Vegas bachelorette trip"}}}'
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()→ returnsbrian@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
cd mcp-server
npm install npx vercel
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)
- Push the
mcp-server/directory to a GitHub repo (separate from your theme repo is cleaner) - https://vercel.com/new → Import Git Repository → pick the mcp-server repo
- Framework Preset → Other
- Root Directory →
mcp-server(if you pushed the parent repo) - Deploy
Custom domain (recommended)
- Vercel dashboard → your project → Domains → Add
mcp.patchistry.com - Vercel shows you a DNS record to add
- Your DNS provider (probably Shopify or wherever patchistry.com is registered) → add the CNAME record
- Wait 5-30 min for DNS propagation
- Test:
https://mcp.patchistry.com/should now return the same JSON
Register the MCP server publicly
Once deployed, list it in the discoverable MCP registries:
Smithery (the leading MCP registry)
- https://smithery.ai
- Sign up → Submit Server
- URL:
https://mcp.patchistry.com/.well-known/mcp.json - Category: Commerce
- Description: "Patchistry commerce tools — modular hats, patches, curated builds, shipping, contact info"
Anthropic MCP Registry (emerging)
Watch https://github.com/modelcontextprotocol/registry — Anthropic is building an official registry. List Patchistry once available.
Direct Claude Desktop integration
Users can manually add the MCP server in Claude Desktop:
- Settings → Developer → MCP Servers → Add Server
- URL:
https://mcp.patchistry.com/sse - Name: Patchistry
Once added, that user's Claude will use Patchistry tools natively — they can ask "what's the bach hat build for Vegas" and Claude pulls live data from your server.
Local development
cd mcp-server
npm install npm start
Server runs at http://localhost:3000
Test with curl:
curl http://localhost:3000/
curl http://localhost:3000/.well-known/mcp.json
Updating the server
The server proxies to https://patchistry.com/products.json and https://patchistry.com/pages/agents-feed for live data — so you don't need to redeploy when products or builds change. The MCP server is essentially a read-only AI-friendly facade over your existing public Shopify endpoints.
Redeploy only when:
- Adding new tools (edit
src/index.js) - Changing data sources
- Updating dependencies
To redeploy after changes:
cd mcp-server
npx vercel --prod
Cost
Vercel Hobby tier (free):
- 100GB-hours/month compute
- Unlimited deployments
- This MCP server will use < 1GB-hour/month at typical AI agent query volumes
- Custom domain free
Total monthly cost: $0 until you hit ~10,000 AI agent queries/day.
What happens after this is deployed
Within 1-2 weeks of deployment + Smithery listing:
- Claude Desktop users with the server added → query Patchistry catalog natively
- AI agent frameworks (LangChain, AutoGPT, etc.) → can discover + use Patchistry tools
- ChatGPT (once OpenAI standardizes MCP for ChatGPT) → can call Patchistry directly
You'll be one of the earliest DTC brands with a public MCP server. That's a defensible positioning advantage in the AI shopping era — the future where AI agents complete purchases on user behalf will heavily favor brands with MCP-native integrations.
Honest framing
This is forward-looking infrastructure. The MCP ecosystem is young in 2026; expect 12-24 months before this drives significant order volume directly.
But:
- The setup cost is one-time + free (Vercel Hobby tier)
- The defensible positioning is real — Smithery listing + direct Claude Desktop integration puts Patchistry in front of every AI-power-user that builds custom agent workflows
- The signal value matters now — having a public MCP server says "AI-native brand" in a way that earns press coverage + founder credibility
Brian, if you deploy this and list it on Smithery, you're in the top 50 DTC brands worldwide with a public MCP commerce server as of 2026. That's a real moat that takes years to dilute.