mcp-netmiko-server
About
An MCP server that enables LLMs interacting with your network devices
Explore
- List network devices defined in a TOML file
- Send arbitrary commands to devices and retrieve output
- Send configuration commands with automatic commit or save
- Supports multiple device platforms via Netmiko (Juniper, Cisco, etc.)
- Default credentials inheritance per TOML section
- Runs as stdio or SSE server
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
mcp-netmiko-serverCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Install
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp-netmiko-server": {
"mcp-netmiko-server": {
"command": "uv",
"args": [
"run",
"--with",
"mcp[cli]",
"--with",
"netmiko",
"main.py",
"my-devices.network.toml"
]
}
}
}
}McpServers
{
"mcp-netmiko-server": {
"command": "uv",
"args": [
"run",
"--with",
"mcp[cli]",
"--with",
"netmiko",
"main.py",
"my-devices.network.toml"
]
}
}An MCP server that enables LLMs interacting with your network devices
via SSH (netmiko).
| Tool | Description |
|:---------------------------------------|:--------------------------------------------------------------------------|
| get_network_device_list | Return list of network device names and types defined in a TOML file. |
| send_command_and_get_output | Send a command to a device and returns its output. |
| set_config_commands_and_commit_or_save | Send configuration commands to a device and commit or save automatically. |
How to use
- Install
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
