Make

You can expose your Make automation workflows as callable tools for AI assistants by running a dedicated MCP server. This server connects to Make, exposes on-demand scenarios with clear parameter descriptions, lets AI systems invoke them with the right inputs, and returns structured results for easy interpretation.

How to use

Set up your MCP client (for example a Claude Desktop app) to connect to the Make MCP server using the provided stdio configuration. The server acts as a bridge: it reads your Make scenarios with On-Demand scheduling, resolves input parameters into human-friendly descriptions, lets you trigger scenarios with those parameters, and returns the results as structured JSON for the AI to consume.

How to install

Prerequisites you need on your machine:

• NodeJS

• MCP Client compatible tool (for example Claude Desktop)

• Make API Key with scenarios:read and scenarios:run scopes

Additional configuration and usage notes

To enable the Make MCP Server with your MCP client, use the following configuration in your MCP client settings under mcpServers. This runs the MCP server via npx with the Make MCP package and passes your API credentials as environment variables.

{
  "mcpServers": {
    "make": {
      "command": "npx",
      "args": ["-y", "@makehq/mcp-server"],
      "env": {
        "MAKE_API_KEY": "<your-api-key>",
        "MAKE_ZONE": "<your-zone>",
        "MAKE_TEAM": "<your-team-id>"
      }
    }
  }
}

Available tools

connect

Connects the MCP server to your Make account and identifies On-Demand scenarios.

resolveInputs

Parses and resolves input parameters for each scenario, providing meaningful parameter descriptions to the AI.

invokeScenario

Allows AI assistants to invoke a Make scenario with the resolved parameters.

getOutput

Returns the scenario output as structured JSON for AI consumption and further automation.