Make MCP Server
Configuration
View docs{
"mcpServers": {
"integromat-make-mcp-server": {
"command": "npx",
"args": [
"-y",
"@makehq/mcp-server"
],
"env": {
"MAKE_TEAM": "<your-team-id>",
"MAKE_ZONE": "<your-zone>",
"MAKE_API_KEY": "<your-api-key>"
}
}
}
}You can expose your Make automation workflows as callable tools for AI assistants using MCP Server. It lets AI systems trigger Make scenarios, supply meaningful input, and receive structured results, enabling bidirectional automation with your existing workflows.
Use this MCP server to turn your Make scenarios into tools that AI assistants can call. The server connects to your Make account, resolves input parameters for each On-Demand scenario, and returns the scenario output as structured JSON so AI systems can interpret the results. You can invoke scenarios with appropriate parameters from AI prompts or tool prompts and use the responses to drive further automation.
Practical usage patterns include: triggering a Make scenario when an AI agent receives a request, passing descriptive parameter values, and handling the resulting data to inform decision making. The server keeps your complex Make logic intact while exposing a clean, structured interface for AI integrations.
Prerequisites before you install: NodeJS and access to an MCP client that can load MCP server configurations (for example, Claude Desktop App). You also need a Make API key with the scopes scenarios:read and scenarios:run.
Add the MCP server configuration to your MCP client’s configuration under mcpServers. Use the following setup to run the MCP server locally through npx.
{
"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>"
}
}
}
}- MAKE_API_KEY is generated in your Make profile. This key authorizes the MCP server to read and invoke scenarios. - MAKE_ZONE is the Make hosting zone for your organization (for example, eu2.make.com). - MAKE_TEAM is the ID of your team, typically found in the Team page URL.