Qontinui Web MCP Server
qontinui-web-mcp
用于 Qontinui Web 平台的 MCP (Model Context Protocol) 服务器。使 AI 助手能够通过 Qontinui API 创建和管理可视化自动化配置。
功能特性
项目管理:创建、读取、更新、删除项目
工作流开发:构建和修改自动化工作流
状态管理:通过识别图像定义 UI 状态
配置导入/导出:完整的配置管理
捕获会话:记录用户操作以进行工作流学习
执行控制:触发并监控自动化运行
Related MCP server: Automatisch MCP Server
安装
cd qontinui-web-mcp
poetry install配置
设置 Qontinui API 的环境变量:
# Development (local)
export QONTINUI_API_URL="http://localhost:8000"
# Production (AWS)
export QONTINUI_API_URL="http://qontinui-prod-py.eba-km2u4s23.eu-central-1.elasticbeanstalk.com"
# Authentication (obtain from Qontinui web app)
export QONTINUI_ACCESS_TOKEN="your-jwt-token"
# OR use credentials
export QONTINUI_EMAIL="your-email@example.com"
export QONTINUI_PASSWORD="your-password"使用方法
在 Claude Desktop 中使用
添加到您的 Claude Desktop 配置 (~/.claude/claude_desktop_config.json) 中:
{
"mcpServers": {
"qontinui-web": {
"command": "poetry",
"args": ["run", "qontinui-web-mcp"],
"cwd": "/path/to/qontinui-web-mcp",
"env": {
"QONTINUI_API_URL": "http://localhost:8000",
"QONTINUI_EMAIL": "your-email@example.com",
"QONTINUI_PASSWORD": "your-password"
}
}
}
}在 Claude Code 中使用
添加到您项目的 .mcp.json 中:
{
"mcpServers": {
"qontinui-web": {
"command": "poetry",
"args": ["run", "qontinui-web-mcp"],
"cwd": "/path/to/qontinui-web-mcp",
"env": {
"QONTINUI_API_URL": "http://localhost:8000"
}
}
}
}可用工具
身份验证
auth_login- 使用邮箱/密码进行身份验证auth_status- 检查当前身份验证状态auth_logout- 清除存储的凭据
项目
list_projects- 列出所有可访问的项目create_project- 创建新项目get_project- 获取项目详情update_project- 更新项目元数据/配置delete_project- 删除项目
配置
export_configuration- 将项目配置导出为 JSONimport_configuration- 将配置导入项目validate_configuration- 验证配置而不进行导入
工作流
create_workflow- 向项目添加工作流update_workflow- 修改现有工作流delete_workflow- 从项目中移除工作流list_workflows- 列出项目中的工作流
状态
create_state- 通过识别图像定义 UI 状态update_state- 修改状态定义delete_state- 从项目中移除状态list_states- 列出项目中的状态
图像
add_image- 向项目添加模式图像list_images- 列出项目中的图像delete_image- 从项目中移除图像
执行
execute_workflow- 在连接的运行器上执行工作流get_execution_status- 检查执行进度cancel_execution- 停止正在运行的工作流
开发
# Install dependencies
poetry install
# Run tests
poetry run pytest
# Format code
poetry run ruff format src/
# Lint (includes import sorting via the `I` rule)
poetry run ruff check src/
# Type check
poetry run mypy src/API 端点
此 MCP 服务器与 Qontinui 后端 API 通信:
环境 | URL |
开发 |
|
生产 |
|
许可证
采用 GNU Affero 通用公共许可证 v3.0 或更高版本 (AGPL-3.0-or-later) 授权。请参阅 LICENSE 获取完整条款。
This server cannot be deployed
Maintenance
Related MCP Connectors
- mcp-serverOAuthcom.make
Give your AI agents the tools to build, manage, and run automation workflows.
- FlowstepOAuthai.flowstep
Generate, inspect, and manage Flowstep UI designs directly from your AI assistant.
AI-powered web automation. Navigate websites using AI agents for one page or a thousand
AI-powered web automation. Navigate websites using AI agents for one page or a thousand
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to manage n8n automation workflows through natural language commands, including creating, executing, monitoring, and organizing workflows with full CRUD operations and execution management.90 npm2MIT
- AlicenseBqualityDmaintenanceEnables AI assistants to interact with Automatisch workflow automation platform, allowing them to create, manage, and monitor workflows, connections, and executions through natural language commands.104 npm7MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to perform intelligent browser automation with session-based context analysis, including navigation, form filling, and content extraction through natural language.MIT

qontinui-lib-mcpofficial
AlicenseNot gradedqualityBmaintenanceEnables AI-powered visual automation workflows by providing tools for searching nodes, creating and validating workflows, and executing automation scripts via natural language.AGPL 3.0