Make MCP Server

Make MCP Server

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 assistants and complex automation ecosystems.

Category
访问服务器

README

Make MCP Server (Fork)

Forked from integromat/make-mcp-server for extension and customization.

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.

Current Capabilities

This fork extends the vanilla MCP server with full scenario lifecycle management:

Scenario Execution (from vanilla)

  • 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 via run_scenario_{id} tools
  • Returns scenario output as structured JSON, enabling AI assistants to properly interpret the results

Scenario Management (this fork)

  • List & View: list_scenarios, get_scenario - List all scenarios with filtering, get full scenario details
  • Create & Clone: create_scenario, clone_scenario - Create new scenarios or duplicate existing ones
  • Update & Delete: update_scenario, delete_scenario - Modify or remove scenarios
  • Blueprint Management: get_blueprint, update_blueprint - View and modify scenario module flow
  • Interface Configuration: set_interface - Define input parameters for on-demand scenarios
  • Activation Control: activate_scenario, deactivate_scenario - Control scenario scheduling
  • Execution Logs: get_logs - View incomplete execution logs (DLQ)

Remaining Limitations

The server does not yet support:

  • Connection management (OAuth, credentials)
  • Webhook creation and configuration
  • Data store operations

API Research

The /research/api/ directory contains comprehensive documentation on the Make.com API, focused on programmatically creating, editing, and managing scenarios:

Document Description
README.md Overview and workflow
scenarios-api.md CRUD operations for scenarios
blueprints-api.md Scenario structure and IML mapping
execution-api.md Running and testing scenarios
modules-apps-api.md Available modules and apps
connections-api.md OAuth and auth management
webhooks-api.md Webhook creation and management
data-stores-api.md Persistent key-value storage
scenario-interface-api.md Input/output definitions
teams-organizations-api.md Team and org management
authentication.md API tokens, scopes, rate limits

Usage with Claude Desktop

Prerequisites

  • NodeJS
  • MCP Client (like Claude Desktop App)
  • Make API Key with appropriate scopes (see below)

Recommended Scopes

For full functionality when extending this server:

  • scenarios:read - List and view scenarios
  • scenarios:write - Create and modify scenarios
  • scenarios:run - Execute scenarios
  • connections:read - View connections
  • connections:write - Create connections
  • hooks:read / hooks:write - Webhook management
  • data-stores:read / data-stores:write - Data store access
  • teams:read - Team information

Installation (Local Build)

  1. Clone this repository
  2. Install dependencies: npm install
  3. Build: npm run build

Add to Claude Desktop config (claude_desktop_config.json):

{
    "mcpServers": {
        "make": {
            "command": "node",
            "args": ["/path/to/make-mcp-server/build/index.js"],
            "env": {
                "MAKE_API_KEY": "<your-api-key>",
                "MAKE_ZONE": "<your-zone>",
                "MAKE_TEAM": "<your-team-id>"
            }
        }
    }
}

Installation (NPX)

For the vanilla upstream version:

{
    "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>"
            }
        }
    }
}

Configuration

  • MAKE_API_KEY - Generate in your Make profile under API Access
  • MAKE_ZONE - Your organization's zone (e.g., us2.make.com, eu1.make.com)
  • MAKE_TEAM - Found in the URL when viewing your Team page

Available Tools

Tool Description
run_scenario_{id} Execute an on-demand scenario (dynamic, one per scenario)
list_scenarios List all scenarios with optional filtering by type/status
get_scenario Get full scenario details including status and scheduling
create_scenario Create a new scenario with optional blueprint and scheduling
update_scenario Update scenario name, folder, blueprint, or scheduling
delete_scenario Permanently delete a scenario
clone_scenario Create a copy of an existing scenario
get_blueprint Get scenario blueprint (module flow and configuration)
update_blueprint Update scenario blueprint
set_interface Define input parameters for on-demand scenarios
get_logs Get incomplete execution logs (DLQ)
activate_scenario Activate scenario for scheduled execution
deactivate_scenario Deactivate scenario

Roadmap

Future extensions planned:

  • [ ] Connection management
  • [ ] Data store operations
  • [ ] Webhook configuration

License

See upstream repository for license information.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选