MultiFlexi MCP Server
MCP server for MultiFlexi API integration, providing tools and resources to manage applications, jobs, companies, users, and run templates.
README
MultiFlexi MCP Server
MCP (Model Context Protocol) Server for MultiFlexi API integration. This server provides tools and resources for interacting with MultiFlexi applications, jobs, companies, users, and run templates.
Features
- Applications: List, retrieve, and manage MultiFlexi applications
- Jobs: Create, retrieve, and monitor job execution
- Companies: Manage company data and configurations
- Users: Access user information and profiles
- Run Templates: Create and update execution templates
- GDPR Compliance: Request and manage data exports
- Authentication: Support for basic authentication
- Error Handling: Comprehensive error handling and logging
Installation
Using pip
pip install multiflexi-mcp-server
From source
git clone https://github.com/VitexSoftware/multiflexi-mcp-server.git
cd multiflexi-mcp-server
pip install -e .
Configuration
The server can be configured using environment variables:
Required Configuration
MULTIFLEXI_HOST: MultiFlexi API host URL (default: demo server)
Optional Configuration
MULTIFLEXI_USERNAME: Username for basic authenticationMULTIFLEXI_PASSWORD: Password for basic authenticationMULTIFLEXI_VERIFY_SSL: Whether to verify SSL certificates (default: true)MULTIFLEXI_TIMEOUT: Request timeout in seconds (default: 30)MULTIFLEXI_MAX_RETRIES: Maximum number of retries (default: 3)MULTIFLEXI_DEBUG: Enable debug logging (default: false)
Example Configuration
export MULTIFLEXI_HOST="https://your-multiflexi-instance.com"
export MULTIFLEXI_USERNAME="your-username"
export MULTIFLEXI_PASSWORD="your-password"
export MULTIFLEXI_VERIFY_SSL="true"
export MULTIFLEXI_DEBUG="false"
Usage
Running the Server
multiflexi-mcp-server
Claude Desktop Integration
Add the following to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"multiflexi": {
"command": "multiflexi-mcp-server",
"env": {
"MULTIFLEXI_HOST": "https://your-multiflexi-instance.com",
"MULTIFLEXI_USERNAME": "your-username",
"MULTIFLEXI_PASSWORD": "your-password"
}
}
}
}
Using with MCP Clients
The server provides the following resources:
multiflexi://apps- List of applicationsmultiflexi://jobs- List of jobsmultiflexi://companies- List of companiesmultiflexi://users- List of usersmultiflexi://runtemplates- List of run templates
Available Tools
Application Management
get_app- Get application by IDget_apps- List all applications (via resources)
Job Management
get_job- Get job by IDcreate_job- Create a new jobget_job_status- Get job execution statusget_jobs- List all jobs (via resources)
Company Management
get_company- Get company by IDget_companies- List all companies (via resources)
User Management
get_user- Get user by IDget_users- List all users (via resources)
Run Template Management
get_runtemplate- Get run template by IDupdate_runtemplate- Update run templateget_runtemplates- List all templates (via resources)
GDPR Compliance
request_data_export- Request data exportget_export_status- Check export status
Example Tool Usage
{
"tool": "get_app",
"arguments": {
"app_id": 123,
"format": "json"
}
}
{
"tool": "create_job",
"arguments": {
"app_id": 123,
"company_id": 456,
"job_data": {
"name": "Data Processing Job",
"description": "Process daily data",
"schedule": "0 2 * * *"
}
}
}
{
"tool": "request_data_export",
"arguments": {
"export_type": "personal_data",
"format": "json"
}
}
Development
Prerequisites
- Python 3.9+
- pip
- virtualenv (recommended)
Setup Development Environment
git clone https://github.com/VitexSoftware/multiflexi-mcp-server.git
cd multiflexi-mcp-server
# Create virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install -e ".[dev]"
Running Tests
pytest
Code Formatting
# Format code
black src/ tests/
# Sort imports
isort src/ tests/
# Type checking
mypy src/
# Linting
ruff src/ tests/
API Documentation
This server integrates with the MultiFlexi API. For detailed API documentation, refer to:
Error Handling
The server provides comprehensive error handling:
- API Errors: Formatted with status codes and detailed messages
- Authentication Errors: Clear authentication failure messages
- Validation Errors: Input validation with descriptive errors
- Network Errors: Timeout and connection error handling
All errors are returned in a consistent JSON format:
{
"error": true,
"operation": "get_app",
"status": 404,
"reason": "Not Found",
"details": {
"message": "Application with ID 123 not found"
}
}
Security Considerations
- Authentication: Use environment variables for credentials
- SSL Verification: Enable SSL verification in production
- Network Security: Ensure secure network connections
- Data Privacy: Handle GDPR exports with appropriate security
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests
- Run the test suite
- Submit a pull request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Support
- Issues: GitHub Issues
- Documentation: GitHub Wiki
- Email: info@vitexsoftware.cz
Changelog
v0.1.0 (Initial Release)
- Basic MCP server implementation
- MultiFlexi API integration
- Application, job, company, user, and template management
- GDPR compliance features
- Comprehensive error handling
- Environment-based configuration
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。