Make
This server enables AI assistants to discover, parameterize, and trigger Make.com automation workflows configured for on-demand execution. It allows users to execute scenarios and receive structured JSON results, bridging the gap between AI assistant
What is Make?
Make is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to this server enables ai assistants to discover, parameterize, and trigger make.com automation workflows configured for on-demand execution. it allows users to execute scenarios and receive structured j...
This server enables AI assistants to discover, parameterize, and trigger Make.com automation workflows configured for on-demand execution. It allows users to execute scenarios and receive structured JSON results, bridging the gap between AI assistant
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- This server enables AI assistants to discover, parameterize,
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @makehq/mcp-serverManual Installation
npx -y @makehq/mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Make
The Make MCP Server connects AI assistants like Claude to Make.com (formerly Integromat) automation workflows, enabling them to discover, parameterize, and trigger scenarios configured for on-demand execution. It bridges natural language interaction with the full power of Make's 1,000+ app integrations, letting you invoke complex multi-step automations simply by describing what you want. Results from executed scenarios are returned as structured JSON, making it easy to chain Make workflows into AI-driven pipelines.
Prerequisites
- Node.js 18 or later installed
- A Make.com account with at least one scenario set to 'On-Demand' scheduling
- A Make API Key with 'scenarios:read' and 'scenarios:run' scopes (generated from your Make profile)
- Your Make organization zone (e.g., eu2.make.com) and Team ID
- An MCP-compatible client such as Claude Desktop
Create a Make API Key
Log in to Make.com, go to your Profile > API, and generate a new API key. Ensure the key has the 'scenarios:read' and 'scenarios:run' scopes. Copy the key and note your organization zone (visible in your browser's URL, e.g., eu2.make.com) and your Team ID (found in the Team page URL).
Set at least one scenario to On-Demand scheduling
In Make.com, open the scenario you want AI assistants to trigger. Click the scheduling button and set it to 'On Demand'. Only on-demand scenarios are exposed by the MCP server.
Add the server to your MCP client configuration
Open your Claude Desktop configuration file and add the Make server entry with your API key, zone, and team ID as environment variables.
{
"mcpServers": {
"make": {
"command": "npx",
"args": ["-y", "@makehq/mcp-server"],
"env": {
"MAKE_API_KEY": "your_make_api_key_here",
"MAKE_ZONE": "eu2.make.com",
"MAKE_TEAM": "your_team_id"
}
}
}
}Restart Claude Desktop
Save the configuration file and restart Claude Desktop. The MCP server will start automatically and connect to your Make account. You should see the Make tools available in the tool list.
Test by listing available scenarios
Ask Claude to list your available Make scenarios. The server will fetch all on-demand scenarios from your team, including their input parameter descriptions, so Claude can prompt you for the right values before running them.
Make Examples
Client configuration
Add this to your Claude Desktop claude_desktop_config.json file. Replace the env values with your actual Make API key, zone, and team ID.
{
"mcpServers": {
"make": {
"command": "npx",
"args": ["-y", "@makehq/mcp-server"],
"env": {
"MAKE_API_KEY": "your_make_api_key_here",
"MAKE_ZONE": "eu2.make.com",
"MAKE_TEAM": "123456"
}
}
}
}Prompts to try
Once configured, try these prompts in Claude Desktop to interact with your Make scenarios.
- "List all my available Make scenarios"
- "Run my 'Send Weekly Report' scenario"
- "Trigger the customer onboarding workflow with email [email protected]"
- "Execute the data sync scenario and show me the results"Troubleshooting Make
No scenarios appear when asking Claude to list them
Ensure your scenarios in Make.com are set to 'On Demand' scheduling — only on-demand scenarios are exposed. Also verify your MAKE_TEAM value is the numeric team ID from the URL, not the team name.
Authentication error: 'Invalid API key' or 403 Forbidden
Check that your MAKE_API_KEY has both 'scenarios:read' and 'scenarios:run' scopes. Regenerate the key in Make > Profile > API if needed. Also confirm MAKE_ZONE matches your organization's hosting region exactly (e.g., eu2.make.com, not make.com).
Scenario runs but returns no data
Make sure your scenario's final module returns output data. Add a 'Set variables' or 'JSON' module at the end of the scenario to format and return structured results that the AI can read.
Frequently Asked Questions about Make
What is Make?
Make is a Model Context Protocol (MCP) server that this server enables ai assistants to discover, parameterize, and trigger make.com automation workflows configured for on-demand execution. it allows users to execute scenarios and receive structured json results, bridging the gap between ai assistant It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Make?
Install via npm with the command: npx -y @makehq/mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Make?
Make works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Make free to use?
Yes, Make is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Make Alternatives — Similar Business Applications Servers
Looking for alternatives to Make? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou
LobeHub
★ 77.5k🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Jeecgboot
★ 46.4kAI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
CowAgent
★ 44.7kCowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Minds Platform
★ 39.2kPlatform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.
Astrbot
★ 32.8kAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Browse More Business Applications MCP Servers
Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Make in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Make?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.