mcpField
I
intertwine-plans

intertwine-plans

Remote
github.com/AtlasDigitalDesignBusiness & Marketing0Updated 4d ago
Repository

About intertwine-plans

intertwine-plans is a read-only MCP server for people searching Angela Kamer's residential house plans. It filters plans by room count, dimensions, foundation and other features, and returns specifications, photos, current prices, and plan links.

Key features

  1. 01Search plans by specs and features
  2. 02Retrieve full details for a named plan
  3. 03Find plans fitting a lot footprint
  4. 04List available styles and features
  5. 05Answer plan purchase questions

Use cases

  1. 01Find an elevated plan with an elevator
  2. 02Filter plans to fit a target lot
  3. 03Compare plan specifications and prices
  4. 04Check what a plan set includes

MCP support

It exposes read-only plan search and reference tools to MCP clients over stateless Streamable HTTP. The server has no authentication and does not write data.

Configuration

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

Endpointhttps://agents.intertwinehouseplans.com/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.

Tools

Details

From the project README

Intertwine House Plans: Plan Finder MCP server

A read-only MCP server that lets AI assistants search the house plans of residential designer Angela Kamer, sold direct at intertwinehouseplans.com. Buyers ask for things like an elevated coastal plan with an elevator under 2,000 square feet, or a plan that fits a 50 by 100 foot lot. The server answers with matching plans, their specs, photos, current prices and a link to each plan's own page.

Endpoint: https://agents.intertwinehouseplans.com/mcp (Streamable HTTP, stateless, no auth) Server card: https://agents.intertwinehouseplans.com/.well-known/mcp/server-card.json Same data as JSON: https://agents.intertwinehouseplans.com/plans.json

Tools

  • search_plans: bedrooms, bathrooms, heated square feet, stories, maximum width and depth, elevated or pilings foundation, elevator, drive-under garage, in-law suite, garage ADU, style (beach, cottage, Low Country, carriage house), words in the description, starting price. Each result has a photo and the current price, with the regular price when a sale is running.
  • get_plan: everything about one plan by name, for example The Heron: specs, garage, ceilings, roof pitch, framing, the smallest lot it suits, foundation options, every package with its price, photos and floor plans, the full write-up, the study set and how to request changes
  • plans_for_lot: plans whose footprint fits a lot after setbacks (a first screen, not a zoning check)
  • list_features: the styles and features, with plan counts
  • about_designer: who draws the plans, file formats, study sets and modifications
  • buying_help: what a plan set includes, study sets, changing a plan, cost to build, plans that have been built, and the store's FAQ

Try it

curl -X POST https://agents.intertwinehouseplans.com/mcp \
  -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search_plans","arguments":{"elevated":true,"elevator":true,"minBedrooms":3}}}'

How it runs

src/worker.js is a Cloudflare Worker. Plan specs are in src/plans.json. Photos, package prices, sale prices, the write-ups, study sets and the FAQ are read from the store's public pages and kept for 30 minutes, so prices are never more than half an hour old. If the store can't be reached, every tool still answers from the specs. Nothing is written and there are no accounts or keys. node test.mjs runs the tests.

Data

68 plan sets (57 house plans and 11 garage ADU plans) by Angela Kamer, residential designer. The plan page is always the source of truth.

Built by Atlas Digital Design.

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.