Skip to main content

Documentation Index

Fetch the complete documentation index at: https://chatbotx.io/docs/llms.txt

Use this file to discover all available pages before exploring further.

MCP (Model Context Protocol) Servers let your AI Agent perform more advanced tasks by connecting directly to external systems and data sources. Example: If you connect to a Shopify MCP Server, your AI Agent can automatically search product details and customer purchase history in real time from your Shopify store. In practice, any system that supports MCP can communicate directly with a ChatbotX AI Agent without requiring you to build complicated custom API integrations yourself.

​
How to connect an MCP Server

To connect a new MCP Server, follow these steps:
  1. Open MCP Servers from the left navigation.
  2. Click + Create MCP Server.
create_mcp_server_button
  1. In the configuration panel, enter the basic connection details:
    • Name: A memorable name for this server, such as Shopify Store or Stripe Billing.
    • URL: The exact URL of the MCP Server you want to connect.
    • Authentication: Choose the security method required by your server, such as None, Token, or Custom Header.
  2. After filling in the URL and Authentication settings, click Get Tools. ChatbotX will automatically scan the MCP Server and load the list of tools it provides.
mcp_server_configuration_modal

​
Enable MCP for an AI Agent

After you add an MCP Server successfully:
  • Open the configuration of the AI Agent that should be allowed to use this server.
  • In the Agent’s tool settings, select the MCP Server you just created to link them together.
ai_agent_select_knowledge_file
At that point, your AI Agent can start calling the available functions from the external system to serve customers. Some popular services and platforms already provide MCP support, including Zapier, Make, Shopify, Stripe, and WooCommerce.