Skip to main content
The Model Context Protocol (MCP) is an open standard that allows AI agents and large language model (LLM) applications to interact with external tools and data sources in a standardized way. HoopAI supports MCP, enabling AI-powered applications to read and write data across the platform.
MCP support is currently in beta. The available tools and capabilities may change as the protocol evolves.

​
What is MCP?

MCP provides a standardized way for AI applications to:
  • Read data from HoopAI (contacts, conversations, calendars, etc.)
  • Take actions in HoopAI (create contacts, send messages, book appointments)
  • React to events using real-time webhooks
Instead of building custom API integrations, AI agents can use MCP tools to interact with HoopAI through a standard interface.

​
Use cases

AI assistants

Build AI chatbots that can look up contacts, check appointment availability, and send messages — all through natural language.

Automated workflows

Let AI agents orchestrate complex business workflows — qualifying leads, scheduling follow-ups, and updating pipelines.

Data analysis

Connect AI models to your HoopAI data for intelligent reporting, forecasting, and insights.

Custom agents

Build specialized AI agents that combine HoopAI data with other MCP-compatible tools.

​
How it works

  1. The AI agent receives a user request in natural language
  2. The agent determines which MCP tools to call
  3. The MCP server translates tool calls into HoopAI API requests
  4. Results flow back to the agent, which generates a response

​
Available MCP tools

The HoopAI MCP server exposes tools for the major platform modules:
Tool categoryCapabilities
ContactsSearch, create, update, tag contacts
ConversationsRead messages, send SMS/email, get conversation history
CalendarsCheck availability, create appointments, manage bookings
OpportunitiesRead pipeline data, update deal stages
PaymentsLook up invoices, check payment status

​
Getting started

1

Set up API access

You’ll need a HoopAI API token. Follow the Authentication guide to get your credentials.
2

Configure the MCP server

Set up the HoopAI MCP server with your API credentials. The server handles translating MCP tool calls into API requests.
3

Connect your AI agent

Configure your MCP-compatible AI agent (Claude, custom agents, etc.) to connect to the HoopAI MCP server.
4

Start using tools

Your AI agent can now interact with HoopAI data using natural language and MCP tools.

​
Example: Claude Desktop integration

To use HoopAI with Claude Desktop, add this to your MCP configuration: 
{
  "mcpServers": {
    "hoopai": {
      "command": "npx",
      "args": ["@hoopai/mcp-server"],
      "env": {
        "HOOPAI_API_TOKEN": "your-api-token",
        "HOOPAI_LOCATION_ID": "your-location-id"
      }
    }
  }
}
The MCP server package name and configuration are examples. Check the latest HoopAI developer resources for the actual package and setup instructions.

​
Next steps

API reference

See all available API endpoints that MCP tools can access

Webhooks

Set up real-time event notifications for your AI workflows
Last modified on March 5, 2026