Tendrils MCP Server

A public remote MCP server exposing real commerce tools for AI agents over JSON-RPC / Streamable HTTP — backed by a live furniture-retail deployment (42,000+ products, 12 vendor feeds, 4 storefronts).

Endpoint: https://tendrils.io/mcp Transport: Streamable HTTP (JSON-RPC 2.0) Auth: none required — rate-limited per IP Server card: https://tendrils.io/.well-known/mcp API spec: https://tendrils.io/openapi.json Docs: https://tendrils.io/developers

Call it

POST https://tendrils.io/mcp
{ "jsonrpc": "2.0", "id": 1, "method": "tools/list" }

Tools

Tool	What it does
find_products_by_constraints	Search the catalog by category, budget, material, features, stock availability
get_product_details	Full specs, parsed dimensions, materials, care, variant matrix
check_variant_availability	Live per-variant stock quantities for option combos
compare_products / compare_products_deep_matrix	Side-by-side spec matrices across frame, fabric, dimensions
create_checkout_handoff	Turn selected variants into a 1-click Shopify checkout URL
calculate_room_fit_and_clearance	Will-it-fit math for sofas/sectionals with walking clearance
generate_room_floorplan	2D SVG architectural floorplan with furniture placement
match_fabric_and_lighting	Match upholstery to room paint and light exposure
get_product_ar_model	Apple QuickLook (.usdz) / Android (.glb) AR model paths
build_coordinated_room_bundle	Anchor piece + matching ottoman/accent chair bundles

Links

• Site: https://tendrils.io
• llms.txt: https://tendrils.io/llms.txt
• OpenAPI: https://tendrils.io/openapi.json