Tendrils — live commerce tools for AI agents
RemoteAbout Tendrils — live commerce tools for AI agents
Tendrils is a remote MCP server for AI agents shopping a live furniture catalog. It supports product discovery, fit and style checks, and checkout handoff.
Key features
- 01Constraint-based catalog search
- 02Product specifications and variants
- 03Live variant stock checks
- 04Product comparison matrices
- 05Room fit and floorplan tools
- 06Shopify checkout handoff
Use cases
- 01Find furniture within budget and material constraints
- 02Check whether a sofa fits a room
- 03Compare product dimensions and fabrics
- 04Prepare a checkout link for selected variants
MCP support
Exposes furniture commerce tools to MCP clients over Streamable HTTP, including catalog search, availability, room planning and checkout handoff.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://tendrils.io/mcpclaude mcp add --transport http io-tendrils https://tendrils.io/mcp{"mcpServers":{"io-tendrils":{"type":"http","url":"https://tendrils.io/mcp"}}}Open in Cursor{"servers":{"io-tendrils":{"type":"http","url":"https://tendrils.io/mcp"}}}Open in VS Code{"mcpServers":{"io-tendrils":{"type":"http","url":"https://tendrils.io/mcp"}}}{"mcpServers":{"io-tendrils":{"serverUrl":"https://tendrils.io/mcp"}}}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 READMETendrils 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
Comments
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.