This MCP server implementation provides network control and management capabilities through the POX SDN controller. It enables Python-based network programming, OpenFlow device management, and automated network analysis through POX's modular architecture, making it ideal for educational environments, network prototyping, and SDN research.
The POX MCP server exposes two dynamic resources:
pox://network-config: A comprehensive POX controller configuration memo that tracks active POX components, records network topology and flow rules, and maintains discovered network insights.
pox://topology: Real-time network topology view showing active OpenFlow datapaths (switches), host locations and connections, and link status with port mappings.
Interactive prompt for POX controller management:
topic
- The network control aspect to focus onBasic L2 hub implementation using POX:
dpid
- The datapath identifierL2 learning switch implementation:
dpid
- The datapath identifierLists all connected OpenFlow datapaths:
Get detailed datapath information:
dpid
(string): Datapath identifierRetrieve POX flow statistics:
dpid
(string): Datapath identifiermatch
(object, optional): POX match structuretable_id
(string, optional): OpenFlow table IDout_port
(string, optional): Output port filterConfigure POX flow tables:
dpid
(string): Datapath identifierflows
(array): POX flow specificationsAdd network insights to POX configuration memo:
insight
(string): Network observation or analysisTo set up the POX MCP server with Claude Desktop, use the following configuration:
{
"mcpServers": {
"pox": {
"command": "uv",
"args": [
"--directory",
"parent_of_servers_repo/servers/src/mcp_server_pox",
"run",
"server.py"
],
"env": {
"POX_SERVER_URL": "http://localhost:8000"
}
}
}
}
Make sure to replace parent_of_servers_repo
with the appropriate path to your server repository. The server will be accessible at the URL specified in the POX_SERVER_URL
environment variable, which is set to http://localhost:8000
by default.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.