MCP Server

Note: Our MCP server is currently in Beta to Pax8 Beyond attendees only. It will be in general release starting mid July 2025.

Unlock the power of integrating your Pax8 data with your favorite Large Language Models (LLMs) using the Pax8 MCP Server. This integration allows you to seamlessly access and interact with your Pax8 information through natural language within AI assistants.

What is the MCP Server?

The Model Context Protocol (MCP) server acts as a secure bridge, enabling AI assistants like Claude, Copilot, and Cursor to access your Pax8 data and perform actions on your behalf.

You can learn more about Model Context Protocol, written by Anthropic the makers of Claude, widely adopted across the industry. https://modelcontextprotocol.io/

Getting Started

Generate a secure MCP token: Obtain a unique token from your Pax8 Marketplace Intergrations Hub → https://app.pax8.com/integrations?tab=mcpServer
Configure your AI Client: Follow the detailed instructions for your client of choice.
Interact with your Pax8 data using natural language: Ask questions and initiate actions using simple, intuitive prompts.

Supported AI Clients

Currently, the MCP Server is compatible with:

Cursor
Claude
Copilot
VSCode

Available Tools

The MCP Server provides access to a variety of tools, allowing you to retrieve specific information and lists from your Pax8 account. Examples include:

Company & Contact Management
Invoices
Order Management
Products
Quoting
Subscriptions

(See the full documentation on the MCP server tab within the Integrations Hub for a complete list of available tools and example prompts.)

Security

Your MCP token is treated with the highest security standards, featuring end-to-end encryption. You maintain control over which API endpoints are accessible and can revoke access at any time. All actions performed through the MCP Server are fully logged and auditable. Remember to treat your MCP server token like a password and do not share it publicly.

Feedback

We value your feedback! If you have any suggestions for improvement, please email us at [email protected].