mcpField
C
Carpetstory

Carpetstory

Remote
carpetstory.oneOther0Updated today

About Carpetstory

Carpetstory is a read-only MCP server for searching the live catalogue of made-to-order, hand-knotted rugs from a Jaipur atelier. It lets shoppers and design professionals browse collections and inspect rug details through MCP clients.

Key features

  1. 01Browse current rug collections
  2. 02Search by motif, mood, colour or place
  3. 03Filter by collection or colour family
  4. 04View rug details, materials and sizes
  5. 05Get images and product links

Use cases

  1. 01Find rugs matching a motif or colour
  2. 02Compare materials and production lead times
  3. 03Check a rug's size and product page

MCP support

Exposes tools to list collections, search rugs and retrieve details for an individual rug. Available as a hosted remote MCP server or for local installation.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://carpetstory.one/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
mcpbcarpetstory.mcpb

Tools

Details

From the project README

Carpetstory MCP server

Search the Carpetstory rug catalogue from Claude, Cursor or any MCP client.

Carpetstory is a rug atelier in Jaipur, India, making hand-knotted rugs to order since 2001. This server reads the live catalogue behind carpetstory.one, so every rug, image and link it returns is current. It is read-only and needs no API key.

Tools

ToolWhat it does
list_collectionsThe current collections with their story, materials, knot density, lead time and number of pieces
search_rugsFind rugs by words (motif, mood, colour, place), optionally within one collection or colour family
get_rugFull details for one rug: description, size, colours, materials, knot density, image and product page

Ask things like:

  • "Show me Carpetstory rugs with a sundial or astronomy motif."
  • "Which hand-knotted rugs come in blue, and how long do they take to make?"
  • "Find an ivory and silk rug for a 9 × 12 ft living room."

Every rug is made to order in any size. Pricing is by enquiry through the enquiry page, and designers and architects can use the trade programme.

Connect

Hosted (no install): add https://carpetstory.one/mcp as a remote MCP server (Streamable HTTP, no authentication).

  • ChatGPT: in Settings, open Connectors (or Apps), turn on Developer mode under Advanced, then create a connector with this URL and "No authentication".
  • Claude (web and desktop): Settings → Connectors → Add custom connector, and paste the URL.
  • Claude Code: claude mcp add --transport http carpetstory https://carpetstory.one/mcp

Install locally

Claude Desktop: download carpetstory.mcpb from the latest release and open it.

Claude Code:

claude mcp add carpetstory -- npx -y github:houseofdotone/carpetstory-mcp

Cursor, Windsurf, Claude Desktop (manual) and other clients:

{
  "mcpServers": {
    "carpetstory": {
      "command": "npx",
      "args": ["-y", "github:houseofdotone/carpetstory-mcp"]
    }
  }
}

Requires Node.js 18 or newer.

Develop

npm install
npm test   # starts the server over stdio and calls every tool against the live catalogue

About Carpetstory

Hand-knotted rugs in wool and silk, designed and woven in Jaipur and made to order for homes, hotels and design studios worldwide. Browse the collections at carpetstory.one or, in Canada, carpetstory.ca.

MIT licensed.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.