netbox-mcp-server
Categories
Language:
Python
Stars:
24
Forks:
5
NetBox MCP Server
This is a simple read-only Model Context Protocol server for NetBox. It enables you to interact with your data in NetBox directly via LLMs that support MCP.
Tools
Tool | Description |
---|---|
get_objects | Retrieves NetBox core objects based on their type and filters |
search_netbox | Performs a global search across NetBox objects |
get_object_by_id | Gets detailed information about a specific NetBox object by its ID |
Note: the set of supported object types is explicitly defined and limited to the core NetBox objects for now, and won't work with object types from plugins.
Usage
-
Create a read-only API token in NetBox with sufficient permissions for the tool to access the data you want to make available via MCP.
-
Install dependencies:
uv add -r requirements.txt
-
Verify the server can run:
NETBOX_URL=https://netbox.example.com/ NETBOX_TOKEN= uv run server.py
-
Add the MCP server configuration to your LLM client. For example, in Claude Desktop (Mac):
{
"mcpServers": {
"netbox": {
"command": "uv",
"args": [
"--directory",
"/path/to/netbox-mcp-server",
"run",
"server.py"
],
"env": {
"NETBOX_URL": "https://netbox.example.com/",
"NETBOX_TOKEN": ""
}
}
}
On Windows, use full, escaped path to your instance, such as
C:\\Users\\myuser\\.local\\bin\\uv
andC:\\Users\\myuser\\netbox-mcp-server
. For detailed troubleshooting, consult the MCP quickstart.
- Use the tools in your LLM client. For example:
> Get all devices in the 'Equinix DC14' site
...
> Tell me about my IPAM utilization
...
> What Cisco devices are in my network?
Development
Contributions are welcome! Please open an issue or submit a PR.
License
This project is licensed under the Apache 2.0 license. See the LICENSE file for details.
Publisher info
NetBox Labs
We make it easier to build and manage networks. The company behind @NetBoxOfficial, #Orb, #Diode, NetBox Cloud and NetBox Enterprise
More MCP servers built with Python
Bridge the gap between your web crawler and AI language models using Model Context Protocol (MCP). With mcp-server-webcrawl, your AI client filters and analyzes web content under your direction or autonomously, extracting insights from your web content. Support for WARC, wget, InterroBot, Katana, and SiteOne crawlers is available out of the gate. The server includes a full-text search interface with boolean support, resource filtering by type, HTTP status, and more.
Armor Model Context Protocol (MCP) gives developers full access to the blockchain functionality of Armor Wallet. This includes cross-chain swaps, token data, bridging, wallet management, limit orders, staking, and many other features. With the Armor MCP, developers can integrate a complete suite of crypto tools available to their AI Agents quickly and easily for fast, reliable AI Agent development.