MCP server docs and changes to build environment

.github/workflows/azure-static-web-apps-delightful-desert-0513ad50f.yml

@@ -35,6 +35,8 @@ jobs:
       - name: Build And Deploy
         id: builddeploy
         uses: Azure/static-web-apps-deploy@v1
+        env:
+          DOCUSAURUS_URL: https://developers.oncehub.com
         with:
           azure_static_web_apps_api_token: ${{ secrets.AZURE_STATIC_WEB_APPS_API_TOKEN_DELIGHTFUL_DESERT_0513AD50F }}
           repo_token: ${{ secrets.GITHUB_TOKEN }} # Used for Github integrations (i.e. PR comments)

.github/workflows/azure-static-web-apps-nice-meadow-0c0634100.yml

@@ -35,6 +35,8 @@ jobs:
       - name: Build And Deploy
         id: builddeploy
         uses: Azure/static-web-apps-deploy@v1
+        env:
+          DOCUSAURUS_URL: https://developers.staticso2.com
         with:
           azure_static_web_apps_api_token: ${{ secrets.AZURE_STATIC_WEB_APPS_API_TOKEN_NICE_MEADOW_0C0634100 }}
           repo_token: ${{ secrets.GITHUB_TOKEN }} # Used for Github integrations (i.e. PR comments)

docs/mcp-server/getting-started.md

@@ -0,0 +1,49 @@
+---
+title: Getting Started with OnceHub MCP Server
+description: Step-by-step guide to configure your AI Agent with the OnceHub MCP Server for automated meeting scheduling.
+---
+
+# Getting Started with OnceHub MCP Server
+
+This section guides you through setting up your environment to use the OnceHub MCP Server. The MCP Server is intended for developers and users familiar with the Model Context Protocol.
+
+To begin, configure your AI Agent with the required server details and API key.
+
+## Step 1: Get your API Key
+
+1. Log in to your OnceHub account.
+2. Click the gear icon in the top-right corner.
+3. Select **Account Integrations** from the dropdown menu.
+4. Click the **APIs & Webhooks** section to generate a unique API Key.
+
+Your AI Agent will use this API Key for authentication.
+
+## Step 2: Configure your MCP Client
+
+Point your MCP-compatible AI Agent or application to the MCP Server endpoint:
+
+```
+https://mcp.oncehub.com/sse
+```
+
+Your AI Agent must include your API key in the request header as follows:
+
+| Header Name | Value            |
+| ----------- | ---------------- |
+| `API-Key`   | `[Your API Key]` |
+
+For details on generating and managing API keys, see [Authentication](/docs/overview/authentication).
+
+## Step 3: Start scheduling by integrating the tool calls
+
+Integrate the two MCP tools into your AI Agent's normal conversation flow. To ensure the Agent interacts with the correct Booking Calendar, you must include the specific Booking Calendar ID in the Agent's system prompt or tool configuration.
+
+- Use **Get available time slots** (`get_booking_time_slots`) to retrieve available meeting slots for your specific Booking Calendar ID.
+- Once a time is confirmed, call **Schedule a meeting** (`schedule_meeting`) to create the appointment.
+
+Once configured, your AI Agent can check availability and schedule meetings entirely through natural-language interaction with you.
+
+**Prompting Tip**
+In your AI Agent's system instructions, specify which Booking Calendar it should work with. For example:
+
+> "If the user needs to meet with a specialist, offer to schedule a meeting using the MCP scheduling tools with Booking Calendar ID: BKC-XXXXXXXX."

docs/mcp-server/introduction.md

@@ -0,0 +1,29 @@
+---
+id: introduction
+title: Introduction to the Model Context Protocol (MCP) Server
+description: Learn how to use the OnceHub MCP Server to enable AI agents to automate meeting scheduling through natural language interaction.
+---
+
+# Introduction to the Model Context Protocol (MCP) Server
+
+## What is the OnceHub MCP Server?
+
+The OnceHub MCP Server provides a standardized way for AI models and agents to interact directly with your OnceHub scheduling API. Rather than sending users a Booking Link and asking them to schedule manually, an AI Agent can retrieve availability and schedule meetings on the user's behalf using MCP tools, through a natural language flow.
+
+This solution enables external AI Agents to access OnceHub scheduling APIs within AI-driven workflows using the standardized Model Context Protocol (MCP) remote server.
+
+## Use Cases
+
+The OnceHub MCP Server is ideal for organizations that:
+
+- Enable AI Agents to automate the meeting scheduling process by calling specialized tools to fetch available slots and schedule meetings during a live conversation.
+
+## Primary Endpoint
+
+AI Agents communicate with the OnceHub scheduling system through the following public MCP endpoint:
+
+```
+https://mcp.oncehub.com/sse
+```
+
+You must configure this endpoint in your MCP compatible AI Agent to begin interacting with the scheduling tools.

docs/mcp-server/tools.md

@@ -0,0 +1,69 @@
+---
+title: MCP Server Tools
+description: Reference documentation for the Get available time slots and Schedule a meeting tools.
+---
+
+# MCP Server Tools
+
+The MCP Server exposes a set of tools that follow the same logic and rules as the existing OnceHub Booking API, but are accessed through the standardized MCP layer.
+
+## 1. Get Available Time Slots
+
+The **Get available time slots** (`get_booking_time_slots`) tool allows an AI Agent to retrieve a list of bookable times for a specific Booking Calendar.
+
+### Function
+
+Retrieves a list of valid bookable time slots within a specified date range.
+
+### How It Works
+
+The tool queries your Booking Calendar's configuration to identify valid available time slots. It respects all supported scheduling settings found on the Booking Settings tab, including:
+
+- Availability
+- Busy times from connected calendar
+- Buffer settings
+
+:::note
+The only exception to the Booking Settings tab is Bookable days; instead the search window is determined by the specific date range provided in the tool request.
+:::
+
+### Date Range Rules
+
+- The date range (start → end) must be less than or equal to 30 days.
+- If no range is provided, the tool searches the next 7 days by default.
+- The start date cannot be in the past.
+
+### Usage
+
+This tool must be the first step in a conversational booking process.
+
+For example, you might ask an AI Agent:
+
+> "Find me a time slot next Tuesday morning."
+
+The AI Agent calls this tool to obtain available times for you to choose from.
+
+## 2. Schedule A Meeting
+
+The **Schedule a meeting** (`schedule_meeting`) tool allows an AI Agent to book a specific time slot on a Booking Calendar.
+
+### Function
+
+Creates a new booking on a Booking Calendar at a time selected from the available slots.
+
+### How It Works
+
+Once you choose a time slot from the results of **Get available time slots**, the AI Agent calls this tool and sends the required details:
+
+- Guest name
+- Guest email
+- Selected Date: Format: `YYYY-MM-DDTHH:MM:SSZ`
+- Start Time: Must be provided in ISO 8601 format
+- Time Zone: Must be provided in IANA Time Zone format (e.g., `America/New_York`)
+- Location (must match with the one returned from previous step)
+
+The tool then finalizes and creates the booking for you.
+
+### Usage
+
+After presenting time options and receiving user confirmation, the AI Agent calls this tool to book the appointment.

sidebars.ts

@@ -50,6 +50,12 @@ const sidebars: SidebarsConfig = {
         "client-side-api/redirecting-booking-confirmation-data",
       ],
     },
+    {
+      type: "category",
+      label: "MCP Server",
+      link: { type: "doc", id: "mcp-server/introduction" },
+      items: ["mcp-server/getting-started", "mcp-server/tools"],
+    },
     {
       type: "category",
       label: "Recipes",