Package

three.ws Concierge

Ask any website's AI concierge a grounded question, and generate the embed to add one to a site.

io.github.nirholas/concierge-mcpSource repository
Version0.1.1latest catalog version
ConnectionPackagenpm
PublishedOct 10, 2026catalog
UpdatedOct 10, 2026catalog
Overview

What this server provides

Ask any website's AI concierge a grounded question, and generate the embed to add one to a site.

Install

Packages

1
Package 1npm
@three-ws/concierge-mcp0.1.1
  • THREE_WS_BASE

    Base URL of the three.ws API that serves POST /api/concierge, and the origin the generated embed snippets point at. Override only when self-hosting or targeting a preview deployment.

    Format: string · Default: https://three.ws
    Optional
  • THREE_WS_TIMEOUT_MS

    Per-request timeout in milliseconds for the concierge answer call. The answer streams over a free-first LLM chain that can fail over across providers, so the default leaves room for one slow rung.

    Format: number · Default: 45000
    Optional
  • CONCIERGE_PAGE_TIMEOUT_MS

    Timeout in milliseconds for fetching a page that concierge_ask grounds its answer in. Separate from the answer timeout so a slow site cannot consume the whole call.

    Format: number · Default: 12000
    Optional
View server metadata