Make
Visit ProjectTurn your Make scenarios into callable tools for AI assistants.
Visit ProjectCategory
Tags
What is Make MCP Server?
The Make MCP Server is a legacy Model Context Protocol (MCP) server that enables AI assistants to utilize Make (formerly Integromat) automation scenarios as callable tools. This integration allows AI systems to trigger and interact with your pre-existing Make workflows, combining the power of AI with your automation logic.
How to use Make MCP Server?
- Prerequisites: Ensure you have NodeJS, an MCP Client (like Claude Desktop), and a Make API Key with the required permissions (
scenarios:read
andscenarios:run
) - Configuration: Add the MCP Server configuration to your Claude Desktop app's config file with your Make credentials:
{ "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>" } } } }```
- Access Scenarios: AI assistants can now discover and invoke your Make scenarios with appropriate parameters.
Key Features of Make MCP Server
- Scenario Integration: Exposes Make scenarios as callable tools for AI assistants
- Parameter Handling: Parses and resolves input parameters, providing AI with meaningful descriptions
- JSON Output: Returns structured results that AI assistants can easily interpret
- Bidirectional Communication: Facilitates two-way exchange between AI and automation workflows
Use Cases of Make MCP Server
- Enabling AI assistants to trigger complex business processes defined in Make
- Automating customer service workflows through AI-initiated Make scenarios
- Creating dynamic AI-driven workflows that combine natural language processing with automation
- Building AI-powered RPA (Robotic Process Automation) solutions
FAQ about Make MCP Server
-
What is the difference between the legacy version and the new version?
The legacy version is the older implementation. For most use cases, we recommend using the new version which is modern and cloud-based.
-
Which Make scenarios can be used with this server?
Only scenarios configured with "On-Demand" scheduling can be utilized by AI assistants through this server.
-
How secure is this integration?
The integration uses API keys and follows Make's security protocols, but you should follow standard practices like keeping your API keys secure and only enabling necessary permissions.
Make MCP Server (legacy)
A modern, cloud-based version of the Make MCP Server is now available. For most use cases, we recommend using this new version.
A Model Context Protocol server that enables Make scenarios to be utilized as tools by AI assistants. This integration allows AI systems to trigger and interact with your Make automation workflows.
How It Works
The MCP server:
- Connects to your Make account and identifies all scenarios configured with "On-Demand" scheduling
- Parses and resolves input parameters for each scenario, providing AI assistants with meaningful parameter descriptions
- Allows AI assistants to invoke scenarios with appropriate parameters
- Returns scenario output as structured JSON, enabling AI assistants to properly interpret the results
Benefits
- Turn your Make scenarios into callable tools for AI assistants
- Maintain complex automation logic in Make while exposing functionality to AI systems
- Create bidirectional communication between your AI assistants and your existing automation workflows
Usage with Claude Desktop
Prerequisites
- NodeJS
- MCP Client (like Claude Desktop App)
- Make API Key with
scenarios:read
andscenarios:run
scopes
Installation
To use this server with the Claude Desktop app, add the following configuration to the "mcpServers" section of your claude_desktop_config.json
:
{
"mcpServers": {
"make": {
"command": "npx",
"args": ["-y", "@makehq/mcp-server"],
"env": {
"MAKE_API_KEY": "", "MAKE_ZONE": "", "MAKE_TEAM": "" } } } } ``` - `MAKE_API_KEY` - You can generate an API key in your Make profile. - `MAKE_ZONE` - The zone your organization is hosted in (e.g., `eu2.make.com`). - `MAKE_TEAM` - You can find the ID in the URL of the Team page.