Make MCP Server

Make MCP server allows external AI systems, such as AI agents, to discover your scenarios and perform tasks for you using those scenarios. Model Context Protocol (MCP) is a communication standard between AI systems and external systems. It enables these systems to easily and safely interact by defining endpoints and providing authentication.

Benefits

  • Turns your scenarios into callable tools for AI

  • Creates bidirectional communication between AI and scenarios

  • Takes advantage of automation logic in Make to give capabilities to AI

How does Make MCP server work?

Make MCP server connects Make to external AI systems in two key ways: exposing all your scenarios scheduled On demand to AI, and allowing AI to run these scenarios as tools. These functions (listing available scenarios and triggering their execution) have their own endpoints, or URLs that allow access to resources from a web service.

You can help your AI system understand what data to receive and send when it uses scenarios as tools by configuring scenario inputs and outputs:

  • Inputs: parameters your AI fills with data when the scenario runs

  • Outputs: data returned from the scenario to your AI

We also strongly recommend adding detailed scenario descriptions. These help your AI understand the purpose of the tool and improve the reliability of your prompts.

Available Make MCP servers

We currently allow two ways to integrate Make MCP server:

The cloud-based MCP server, hosted by Make, runs via Server-Sent Events (SSE). It is suitable for any integration and environment.

The local MCP server is a basic version that runs locally on your machine. It is ideal for scenarios that require local management and control, and when you have significant technical expertise.

Last updated