MCP Protocol (AI Agent Access)
The EquipDash MCP server enables AI assistants to interact with your EquipDash account using the Model Context Protocol. This gives AI tools like ChatGPT, Claude, and Gemini direct access to your bookings, products, customers, and more through natural language.
What is MCP?โ
MCP (Model Context Protocol) is an open standard that lets AI assistants call tools and access data from external services. Instead of writing API calls manually, you describe what you want in plain English and the AI agent handles the rest.
Endpointโ
POST https://app.equipdash.com/mcp/v1
Transport: Streamable HTTP (JSON-RPC over HTTP POST)
When to Use MCP vs REST APIโ
| Use Case | MCP | REST API |
|---|---|---|
| AI assistant managing bookings via natural language | Yes | |
| Connecting ChatGPT, Claude, or Gemini to your account | Yes | |
| Building a custom website or app integration | Yes | |
| Automated scripts and cron jobs | Yes | |
| Webhook-driven workflows | Yes | |
| Bulk data import/export | Yes | |
| Real-time availability on your website | Yes |
Rule of thumb: Use MCP when an AI agent is the consumer. Use the REST API when your code is the consumer.
Supported Clientsโ
Any MCP-compatible AI assistant can connect to the EquipDash MCP server:
- ChatGPT - OpenAI's AI assistant (Desktop and web)
- Claude - Anthropic's AI assistant (web, desktop and mobile apps, as a custom connector)
- Gemini - Google's AI assistant
- Custom agents - Any application implementing the MCP client protocol
Available Tool Domainsโ
The MCP server exposes 114 tools organized across 21 domains:
| Domain | Tools | Description |
|---|---|---|
| Bookings | 12 | List, create, update, cancel bookings; manage notes and tags; track late pickups/returns |
| Products | 8 | Manage rental products, check availability, calculate pricing, track inventory |
| Experiences | 6 | Manage tours/activities, check schedules, view availability |
| Customers | 7 | Search, create, update customers; manage notes |
| Staff | 8 | Manage staff members, shifts, and schedules |
| Payments | 11 | Record payments, process refunds, send payment links, manage charges |
| Reports | 7 | Revenue summaries, booking stats, trends, top performers |
| Promotions | 8 | Manage promo codes and gift vouchers |
| Store | 8 | Manage store products, inventory, and sales stats |
| Forms | 5 | View waivers/forms, check completion status, send to customers |
| Surveys | 3 | View surveys, NPS analytics, and trends |
| Tags | 1 | List booking tags |
| Workshop | 3 | View workshop items, details, and barcode lookups |
| Bundles | 3 | List bundles, get details, check availability |
| Categories | 9 | Manage product, experience, and store categories |
| Waitlist | 4 | View waitlist, add entries, notify customers, view stats |
| Support | 3 | List, view, and create support tickets |
| Campaigns | 2 | View email campaigns and performance stats |
| Seasons | 2 | List and create pricing seasons |
| Settings | 2 | View business hours and locations |
| AI Credits | 2 | Check AI credit balance and usage |
How It Worksโ
- Your AI client connects to
https://app.equipdash.com/mcp/v1with your API key - The server advertises available tools based on your API key's scopes and the supplier's enabled modules (see below)
- The AI calls tools as needed to fulfill your requests
- Results are returned as structured JSON
Per-supplier tool filtering (Rentals / Experiences / Store)โ
Each EquipDash supplier can enable or disable the Rentals, Experiences,
and Store modules independently from their settings. The MCP server
advertises only the tools whose module is enabled for the requesting
supplier โ so an experiences-only supplier never sees list_products,
adjust_store_inventory, etc., and the AI never proposes calling them.
| Disabled module | Tools that disappear from tools/list |
|---|---|
| Rentals | All Products, Bundles, Workshop tools, the rental-specific category tools, and rental-only reports (get_top_products, get_inventory_report) |
| Experiences | All Experiences tools, experience-specific category tools, and get_top_experiences |
| Store | All Store tools and store-specific category tools |
Module-agnostic tools (Bookings, Customers, Staff, Payments, Help Centre, AI Credits, etc.) are always available regardless of module state.
If a tool is somehow invoked for a disabled module (stale client cache,
race with a toggle), the call returns a runtime error explaining which
module is off. Mirror this in your client by re-fetching
GET /supplier/modules and refreshing
your tool list.
Next Stepsโ
- Authentication - Set up your API key for MCP access
- Quickstart - Configure ChatGPT, Claude, or Gemini
- Tool Reference - Browse all available tools
- Examples - Common workflow examples