Observium MCP Server
Enables natural language queries about device status, network traffic, sensor readings, alerts, and historical trends from Observium CE network monitoring.
README
Observium MCP Server
A Model Context Protocol (MCP) server that exposes Observium CE network monitoring data to LLMs like Claude, enabling natural language queries about device status, network traffic, sensor readings, alerts, and historical trends.
Features
- Device Management: List and query monitored devices with status, uptime, and hardware info
- Network Ports: View interface status, traffic rates, and utilization
- Sensors: Access temperature, voltage, frequency, and other sensor data
- Alerts: Query active and historical alerts with summaries
- Trends: Retrieve historical metrics from RRD data (load, CPU, memory)
Requirements
- Python 3.10+ (required by MCP SDK)
- Observium CE installation with MySQL/MariaDB database access
- Access to Observium's RRD data directory (for trend data)
rrdtoolandlibrrd-devpackages (for RRD data access)
Installation
1. Clone the repository
git clone https://github.com/kdesch5000/observium-mcp.git
cd observium-mcp
2. Create a virtual environment
python3 -m venv venv
source venv/bin/activate
3. Install dependencies
pip install -r requirements.txt
4. Configure environment
Copy the example configuration and edit with your Observium database credentials:
cp config.example.env .env
Edit .env with your settings:
# Database connection (use SSH tunnel if remote)
OBSERVIUM_DB_HOST=localhost
OBSERVIUM_DB_PORT=3306
OBSERVIUM_DB_NAME=observium
OBSERVIUM_DB_USER=observium
OBSERVIUM_DB_PASS=your_database_password
# RRD data path (on the Observium server)
OBSERVIUM_RRD_PATH=/opt/observium/rrd
# Optional: SSH configuration for remote RRD access
# If MCP server runs on a different machine than Observium,
# set these to enable SSH-based RRD file access for trend data
# OBSERVIUM_RRD_SSH_HOST=observium.example.com
# OBSERVIUM_RRD_SSH_USER=pi
# OBSERVIUM_RRD_SSH_PORT=22
Usage
With Claude Code
Add to your Claude Code MCP configuration (~/.claude/claude_code_config.json):
{
"mcpServers": {
"observium": {
"command": "python",
"args": ["-m", "observium_mcp.server"],
"cwd": "/path/to/observium-mcp/src",
"env": {
"OBSERVIUM_DB_HOST": "localhost",
"OBSERVIUM_DB_NAME": "observium",
"OBSERVIUM_DB_USER": "observium",
"OBSERVIUM_DB_PASS": "your_password",
"OBSERVIUM_RRD_PATH": "/opt/observium/rrd"
}
}
}
}
With Claude Desktop
Add to your Claude Desktop configuration:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"observium": {
"command": "python",
"args": ["-m", "observium_mcp.server"],
"cwd": "/path/to/observium-mcp/src",
"env": {
"OBSERVIUM_DB_HOST": "your_observium_host",
"OBSERVIUM_DB_NAME": "observium",
"OBSERVIUM_DB_USER": "observium",
"OBSERVIUM_DB_PASS": "your_password",
"OBSERVIUM_RRD_PATH": "/opt/observium/rrd"
}
}
}
}
Standalone
cd src
python -m observium_mcp.server
Available Tools
| Tool | Description |
|---|---|
list_devices |
List all monitored devices with status |
get_device |
Get detailed info for a specific device |
list_ports |
List network interfaces for a device |
get_port_traffic |
Get traffic stats for a specific port |
list_sensors |
List sensor readings (temp, voltage, etc.) |
list_alerts |
List active or historical alerts |
get_alert_summary |
Get alert count summary |
get_trends |
Get historical metric data |
list_available_metrics |
List available RRD metrics for a device |
Example Queries
Once connected, you can ask Claude questions like:
- "What devices are currently down?"
- "Show me the temperature sensors on the main switch"
- "What's the CPU load trend for the firewall over the past week?"
- "Are there any active alerts?"
- "Which ports on the core switch have errors?"
- "What's the uptime of all my Linux servers?"
Remote Access
If your Observium instance is on a remote server, you have several options:
Option 1: SSH Tunnel
# Create SSH tunnel to forward MySQL port
ssh -L 3306:localhost:3306 user@observium-server
# Then configure .env with localhost
OBSERVIUM_DB_HOST=localhost
Option 2: Install on Observium Server
Install the MCP server directly on the Observium host and configure Claude to connect via SSH.
Option 3: Network Access
If MySQL is accessible on the network (not recommended for security):
OBSERVIUM_DB_HOST=observium.example.com
Security Considerations
- Database credentials are stored in
.envwhich is gitignored - The server only performs SELECT queries (read-only)
- Consider using a read-only MySQL user for additional safety
- RRD access is read-only via
rrdtool fetch
Creating a Read-Only Database User
For additional security, create a dedicated read-only MySQL user:
CREATE USER 'observium_mcp'@'localhost' IDENTIFIED BY 'secure_password';
GRANT SELECT ON observium.* TO 'observium_mcp'@'localhost';
FLUSH PRIVILEGES;
Troubleshooting
Connection refused
- Verify MySQL is running and accessible
- Check database credentials in
.env - Ensure the MySQL user has SELECT permissions
No RRD data / Trend tools failing
- Verify
OBSERVIUM_RRD_PATHpoints to the correct directory on the Observium server - If running MCP on a different machine, configure SSH access:
- Set
OBSERVIUM_RRD_SSH_HOSTto the Observium server hostname - Set
OBSERVIUM_RRD_SSH_USERto a user with SSH access - Ensure SSH key-based authentication is configured
- Set
- Ensure
rrdtoolis installed on the Observium server (for remote) or locally - Check file permissions on the RRD directory
Module not found
Make sure you're running from the src directory or have installed the package:
cd /path/to/observium-mcp/src
python -m observium_mcp.server
Contributing
Contributions are welcome! Please feel free to submit issues and pull requests.
License
MIT License - see LICENSE for details.
Acknowledgments
- Observium - Network monitoring platform
- Model Context Protocol - The MCP specification
- Anthropic - Claude and MCP development
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。