Design
patchdesign.ai
An MCP server for PatchDesign that enables users to design, price, edit, and order custom patches from chat.
ENDPOINT 1
https://patchdesign.ai/api/mcp
MCP server metadata
- Name
- patchdesign-ai
- Version
- 1.0.0
PatchDesign.AI designs custom patches (embroidered, woven, chenille, printed, PVC) and prices them from the live production price table. Prices are USD and already include artwork, a pre-production sample, expert review and worldwide shipping; there is no setup fee. Runs start at 10 pieces (5 for chenille, 25 for woven and printed); a single patch is sold as a sample. design_patch and edit_patch each generate one image and take 15 to 30 seconds. The preview they return is the picture of the design: show it (or its preview link) to the user with its D- number, because it is exactly what gets made and the order link opens that same design. It is the only picture of the design; any other image shows a patch that is not the design. To change a design, even many turns later, use edit_patch with its id (d_...) from the result of that design, not its D- number; starting over would lose the artwork. Each version gets its own preview and D- number. Give every link exactly as returned. Previews carry a light watermark; the clean file comes with the order. A chat gets 10 free designs. When a tool says the limit is reached, give the user the sign-in link and wait for them to connect; do not retry in a loop. Nothing is ordered or charged from the chat. order_link opens the design on patchdesign.ai where the user pays. Do not promise a delivery date: production takes about 10 business days after artwork approval, plus shipping.
Known tools 5
design_patchGenerate a production-ready custom patch design from a description (and optionally a reference image URL).
Inferred read-onlyorder_linkThe link where the user orders a design from this chat, with the type, size and quantity set, plus the price for that quantity.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.patchdesign-ai]
url = "https://patchdesign.ai/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"patchdesign-ai": {
"type": "http",
"url": "https://patchdesign.ai/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: patchdesign-ai
Remote MCP URL: https://patchdesign.ai/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"patchdesign-ai": {
"url": "https://patchdesign.ai/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"patchdesign-ai": {
"type": "http",
"url": "https://patchdesign.ai/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "patchdesign-ai",
"transport": "streamable-http",
"url": "https://patchdesign.ai/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.