
Ceph MCP Server
A Model Context Protocol server that enables AI assistants to interact with Ceph storage clusters through natural language, making storage management more accessible and intuitive.
README
Ceph MCP Server
A Model Context Protocol (MCP) server that enables AI assistants to interact with Ceph storage clusters through natural language. This server provides a bridge between AI tools and your Ceph infrastructure, making storage management more accessible and intuitive.
🚀 Features
- Health Monitoring: Get comprehensive cluster health status and diagnostics
- Host Management: Monitor and manage cluster hosts and their services
- Detailed Analysis: Access detailed health checks for troubleshooting
- Secure Communication: Authenticated access to Ceph Manager API
- Structured Responses: AI-friendly output formatting for clear communication
- Async Architecture: Non-blocking operations for better performance
📋 Prerequisites
- Python 3.11 or higher
- UV package manager
- Access to a Ceph cluster with Manager API enabled
- Valid Ceph credentials with appropriate permissions
🛠️ Installation
- Clone and setup the project:
# Create the project directory
mkdir ceph-mcp-server
cd ceph-mcp-server
# Initialize UV project
uv init --python 3.11
# Add dependencies
uv add mcp httpx pydantic python-dotenv structlog asyncio-mqtt
uv add --dev pytest pytest-asyncio black isort mypy ruff
- Set up your environment:
# Copy the example environment file
cp .env.example .env
# Edit .env with your Ceph cluster details
nano .env
- Configure your Ceph connection:
# .env file contents
CEPH_MANAGER_URL=https://192.16.0.31:8443
CEPH_USERNAME=admin
CEPH_PASSWORD=your_ceph_password
CEPH_SSL_VERIFY=false # Set to true in production with proper certificates
🏃♂️ Quick Start
- Start the MCP server:
uv run python -m ceph_mcp.server
- Test the connection: The server will log its startup and any connection issues. Look for messages indicating successful connection to your Ceph cluster.
🔧 Configuration
Environment Variables
Variable | Description | Default | Required |
---|---|---|---|
CEPH_MANAGER_URL |
Ceph Manager API endpoint | https://192.16.0.31:8443 |
Yes |
CEPH_USERNAME |
Ceph username for API access | admin |
Yes |
CEPH_PASSWORD |
Ceph password for authentication | - | Yes |
CEPH_SSL_VERIFY |
Enable SSL certificate verification | true |
No |
CEPH_CERT_PATH |
Path to custom SSL certificate | - | No |
LOG_LEVEL |
Logging level (DEBUG, INFO, WARNING, ERROR) | INFO |
No |
MAX_REQUESTS_PER_MINUTE |
Rate limiting for API requests | 60 |
No |
Security Considerations
- Production Usage: Always enable SSL verification (
CEPH_SSL_VERIFY=true
) in production - Credentials: Store credentials securely and never commit them to version control
- Network Access: Ensure the MCP server can reach your Ceph Manager API endpoint
- Permissions: Use a dedicated Ceph user with minimal required permissions
🎯 Available Tools
The MCP server provides four main tools for AI assistants:
1. get_cluster_health
Get comprehensive cluster health status including overall health, warnings, and statistics.
Use cases:
- "How is my Ceph cluster doing?"
- "Are there any storage issues I should know about?"
- "What's the current status of my cluster?"
2. get_host_status
Retrieve information about all hosts in the cluster including online/offline status and service distribution.
Use cases:
- "Which hosts are online in my cluster?"
- "What services are running on each host?"
- "Are any hosts having problems?"
3. get_health_details
Get detailed health check information for troubleshooting specific issues.
Use cases:
- "What specific warnings does my cluster have?"
- "Give me detailed information about cluster errors"
- "Help me troubleshoot this storage issue"
4. get_host_details
Get comprehensive information about a specific host.
Parameters:
hostname
: The name of the host to examine
Use cases:
- "Tell me about host ceph-node-01"
- "What services are running on this specific host?"
- "Get detailed specs for this host"
📊 Example Interactions
Health Check
AI Assistant: "How is my Ceph cluster doing?"
Response: ✅ Cluster is healthy. All 3 hosts are online. OSDs: 12/12 up.
🟢 Overall Status: HEALTH_OK
🖥️ Hosts: 3/3 online
💾 OSDs: 12/12 up
Troubleshooting
AI Assistant: "What warnings does my cluster have?"
Response: 🟡 Cluster has 2 warning(s) requiring attention.
🟡 Warnings requiring attention:
- OSD_NEARFULL: 1 osd(s) are getting full
- POOL_BACKFILLFULL: 1 pool(s) are backfill full
🧪 Development
Running Tests
# Run all tests
uv run pytest
# Run with coverage
uv run pytest --cov=ceph_mcp
# Run specific test types
uv run pytest -m "not integration" # Skip integration tests
Code Quality
# Format code
uv run black src/ tests/
uv run isort src/ tests/
# Lint code
uv run ruff check src/ tests/
uv run mypy src/
# All checks
uv run ruff check src/ tests/ && uv run mypy src/ && uv run pytest
Project Structure
ceph-mcp-server/
├── src/ceph_mcp/
│ ├── __init__.py # Package initialization
│ ├── server.py # Main MCP server
│ ├── api/
│ │ └── ceph_client.py # Ceph API client
│ ├── config/
│ │ └── settings.py # Configuration management
│ ├── handlers/
│ │ └── health_handlers.py # Request handlers
│ ├── models/
│ │ └── ceph_models.py # Data models
│ └── utils/ # Utility functions
├── tests/ # Test suite
├── .env.example # Environment template
├── pyproject.toml # Project configuration
└── README.md # This file
🐛 Troubleshooting
Common Issues
-
Connection Refused
- Check if Ceph Manager is running and accessible
- Verify the URL and port in your configuration
- Ensure network connectivity between MCP server and Ceph cluster
-
Authentication Failed
- Verify username and password are correct
- Check that the user has appropriate permissions
- Ensure the Ceph user account is active
-
SSL Certificate Errors
- For development: Set
CEPH_SSL_VERIFY=false
- For production: Use proper SSL certificates or specify
CEPH_CERT_PATH
- For development: Set
-
Permission Denied
- Ensure the Ceph user has read permissions for health and host information
- Check Ceph user capabilities:
ceph auth get client.your-username
Debugging
Enable debug logging to get more detailed information:
LOG_LEVEL=DEBUG uv run python -m ceph_mcp.server
🤝 Contributing
- Fork the repository
- Create a feature branch:
git checkout -b feature-name
- Make your changes and add tests
- Run the test suite:
uv run pytest
- Format code:
uv run black src/ tests/
- Submit a pull request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
- Ceph Storage - The distributed storage system
- Model Context Protocol - The protocol enabling AI integration
- Anthropic - For developing MCP and Claude
📞 Support
- Create an issue for bug reports or feature requests
- Check existing issues before creating new ones
- Provide detailed information about your environment when reporting issues
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。