Model Context Protocol (MCP) servers extend your chatbot’s capabilities by connecting it to external services and data sources. This guide explains how to set up and use MCP servers in your chatbot with the recommended Zapier MCP Hub integration.
MCP servers act as bridges between your chatbot and external services, allowing it to:
Use claude 4 sonnet, gpt 4o, gemini 2.5 flash models for best results. Other models may not work as expected.
Visit Zapier MCP Hub:
Get your endpoint:
Install in your chatbot:
Get the HTTP streaming endpoint:
Install the Server:
For advanced users who want to run local MCP servers:
Run an MCP SSE proxy to turn your local MCP server into a remote one. This example repo shows you how to run an MCP proxy to turn a local MCP server into a remote / SSE MCP server. If you follow this route, you will need to make sure you expose to appropriate ports via ngrok or similar tools.
For services requiring authentication (e.g., Google Sheets, Google Calendar):
MCP servers can be enable for public use (meaning through web chatbot, social media, etc.) by enabling the “Public” option in the server settings.
Server Management:
Security:
Performance:
For the fastest setup experience:
Connection Problems:
Authentication Errors:
Performance Issues:
Server Type Issues: