RouterOS MCP Server
Enables AI assistants to interact with MikroTik RouterOS devices through API and SSH connections, supporting network monitoring, configuration management, and diagnostics across multiple routers with automatic connection fallback.
README
RouterOS MCP Server
A Model Context Protocol (MCP) server for interacting with MikroTik RouterOS devices. This server provides AI assistants with comprehensive access to RouterOS devices through both API and SSH connections, with automatic fallback mechanisms for reliability.
Features
- Multiple Connection Methods: API (port 8728), API with SSL (port 8729), and SSH (port 22)
- Automatic Fallback: Tries connection methods in configurable order until successful
- Multi-Device Support: Manage multiple RouterOS devices from a single MCP server
- Comprehensive Tools: System info, interfaces, IP addresses, routes, neighbors, bridges, logs, config export, and ping
- Smart Configuration Export: Automatically falls back to SSH when API permissions are insufficient
- DNS Fallback: Supports fallback IP addresses when DNS resolution fails
- Flexible Configuration: YAML-based device configuration with environment variable overrides
- Type Safety: Full type hints and pydantic-based settings validation
Installation
Using UV (recommended)
cd routeros_mcp
uv sync
Using pip
cd routeros_mcp
pip install -e .
Configuration
Device Configuration
Create a devices.yaml file in one of these locations:
etc/devices.yaml(in the package directory)- Or specify a custom path with
ROUTEROS_DEVICES_CONFIGenvironment variable
Example devices.yaml:
devices:
- name: core-gw
hostname: core-gw.example.com
username: admin
password: your-password
disabled: false
fallback_ip: 10.26.0.1 # Optional: used if DNS fails
private_key: null # Optional: SSH private key path
- name: branch-router
hostname: 192.168.1.1
username: admin
password: another-password
disabled: false
fallback_ip: null
private_key: null
See etc/devices.yaml.example for a complete example.
Environment Variables (Optional)
Create a .env file to customize connection settings:
# RouterOS connection settings (defaults shown)
ROUTEROS_API_PORT=8728
ROUTEROS_API_SSL_PORT=8729
ROUTEROS_SSH_PORT=22
ROUTEROS_TIMEOUT=10
ROUTEROS_CONNECTION_ORDER=api,api_ssl,ssh
# Path to devices.yaml
ROUTEROS_DEVICES_CONFIG=/path/to/devices.yaml
# Logging level
ROUTEROS_LOG_LEVEL=INFO
See .env.example for all available options.
Usage
Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"routeros": {
"command": "uv",
"args": [
"--directory",
"/path/to/routeros-mcp",
"run",
"routeros-mcp"
]
}
}
}
See etc/claude_desktop_config_example.json for more options.
Command Line
# With UV
uv run routeros-mcp
# With Python
python -m routeros_mcp
Available Tools
Device Management
list_devices()- List all configured RouterOS devicessystem_info(device_name)- Get system information (CPU, memory, uptime, version, etc.)
Network Information
interfaces(device_name, include_disabled)- List network interfaces with statusip_addresses(device_name)- List IP addresses configured on interfacesip_routes(device_name, only_active)- List routing table entriesneighbors(device_name)- List discovered neighbors (CDP/LLDP)bridges(device_name)- List Layer 2 bridge configurations
Monitoring
logs(device_name, topics, limit, offset)- Get device logs with pagination and filtering
Configuration & Diagnostics
config(device_name)- Get full configuration export (with automatic SSH fallback)ping(device_name, address, count, size, interval, timeout)- Execute ping from device
Advanced
command(device_name, command, parameters_json)- Execute any RouterOS API command
Tool Examples
List Devices
Tool: list_devices
Returns: [{"name": "core-gw", "hostname": "192.168.1.1", ...}]
Get System Information
Tool: system_info
Parameters:
- device_name: "core-gw"
Returns: {"success": true, "info": {"version": "7.12", "uptime": "2w3d", ...}}
Get Filtered Logs
Tool: logs
Parameters:
- device_name: "core-gw"
- topics: "ospf,error" # Comma-separated regex patterns
- limit: 20
- offset: 0
Returns: {"logs": [...], "total_available": 150, "total_returned": 20}
Execute Custom API Command
Tool: command
Parameters:
- device_name: "core-gw"
- command: "/ip/firewall/filter/print"
- parameters_json: "{}"
Returns: {"success": true, "result": [...]}
Ping from Router
Tool: ping
Parameters:
- device_name: "core-gw"
- address: "8.8.8.8"
- count: 5
Returns: {"results": [...], "summary": {"sent": 5, "received": 5, "packet_loss_percent": 0}}
Available Resources
routeros://inventory- Real-time device inventoryrouteros://device/{device_name}/status- Live device statusrouteros://device/{device_name}/config- Current device configuration
Connection Methods
The server tries connection methods in the order specified by ROUTEROS_CONNECTION_ORDER (default: api, api_ssl, ssh):
- API (port 8728): RouterOS API v2 without SSL - fastest method
- API SSL (port 8729): RouterOS API v2 with SSL encryption
- SSH (port 22): Fallback method using SSH commands
Notes on Permissions
- Read-only API access: Most tools work with read-only API permissions
- Configuration export: Requires read-write API permissions OR falls back to SSH automatically
- Ping: Always uses SSH (not available via API)
Security Considerations
- Store
devices.yamlsecurely as it contains passwords devices.yamlis in.gitignoreby default- Consider using environment variables for sensitive data in production
- API connections use plaintext authentication (required for RouterOS 6.43+)
- SSL verification is disabled for API SSL connections (common for self-signed certs)
Troubleshooting
Device Not Found
- Check that device name matches exactly in
devices.yaml - Ensure device is not marked as
disabled: true - Verify
devices.yamlis in a searched location
Connection Failures
- Verify hostname/IP is reachable:
ping <hostname> - Check RouterOS API is enabled:
/ip service print(look for api/api-ssl) - Verify SSH is enabled:
/ip ssh print - Test credentials manually
- Check firewall rules allow connections on required ports
- Review server logs for detailed error messages
Configuration Export Fails
- Requires read-write API permissions OR SSH access
- Server automatically falls back to SSH if API fails
- Check that user has
/exportcommand permissions
DNS Resolution Issues
- Use
fallback_ipin device configuration - Server automatically uses fallback IP if DNS fails
Development
Project Structure
routeros-mcp/
├── pyproject.toml
├── README.md
├── LICENSE
├── .env.example
├── .gitignore
├── etc/
│ ├── claude_desktop_config_example.json
│ └── devices.yaml.example
└── src/
└── routeros_mcp/
├── __init__.py
├── __main__.py # Entry point
├── server.py # MCP server and tools
├── client.py # RouterOS API/SSH client
├── settings.py # Configuration management
└── exceptions.py # Custom exceptions
Running Tests
# Install development dependencies
uv sync --dev
# Run tests (if available)
pytest
# Type checking
mypy src/routeros_mcp
Adding New Tools
- Add the core function to
server.py(e.g.,_routeros_new_feature()) - Add MCP tool wrapper with
@mcp.tool()decorator - Add comprehensive docstring with parameter descriptions
- Update README.md with examples
RouterOS API Reference
Common API command paths (use with routeros_command):
/system/resource/print- System resources/interface/print- Network interfaces/ip/address/print- IP addresses/ip/route/print- Routing table/ip/firewall/filter/print- Firewall rules/ip/firewall/nat/print- NAT rules/routing/ospf/neighbor/print- OSPF neighbors/routing/bgp/peer/print- BGP peers/system/identity/print- System identity/system/clock/print- System time/log/print- System logs
For complete API documentation, see: https://help.mikrotik.com/docs/spaces/ROS/pages/47579160/API
License
MIT License - see LICENSE file for details.
Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch
- Make your changes with tests
- Submit a pull request
Support
- RouterOS Documentation: https://help.mikrotik.com/docs/spaces/ROS/
- RouterOS API Documentation: https://help.mikrotik.com/docs/spaces/ROS/pages/47579160/API
- MCP Documentation: https://modelcontextprotocol.io/
Changelog
0.1.0 (Initial Release)
- Multi-device support with YAML configuration
- API, API SSL, and SSH connection methods
- Automatic fallback mechanisms
- Comprehensive RouterOS tools and resources
- Environment-based configuration
- Full type safety with pydantic
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。