POX MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@POX MCP Server list all connected OpenFlow switches"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
POX MCP Server
Overview
A Model Context Protocol (MCP) server implementation that provides network control and management capabilities through the POX SDN controller. This server enables Python-based network programming, OpenFlow device management, and automated network analysis through POX's modular architecture. Perfect for educational environments, network prototyping, and SDN research.
Related MCP server: F5 MCP Server
Components
Resources
The server exposes two dynamic resources:
pox://network-config: A comprehensive POX controller configuration memoTracks active POX components and their configurations
Records network topology and flow rules
Maintains discovered network insights
pox://topology: Real-time network topology viewShows active OpenFlow datapaths (switches)
Maps host locations and connections
Displays link status and port mappings
Prompts
The server provides three specialized prompts:
pox-network-manager: Interactive prompt for POX controller managementRequired argument:
topic- The network control aspect to focus onHelps configure POX components and modules
Guides through network policy implementation
Integrates with network configuration memo
simple-hub: Basic L2 hub implementation using POXRequired argument:
dpid- The datapath identifierDemonstrates POX's event-driven programming
Shows basic packet handling and flooding
Explains POX's core mechanisms
learning-switch: L2 learning switch implementationRequired argument:
dpid- The datapath identifierShowcases POX's table management
Implements MAC learning and forwarding
Demonstrates POX's packet handling capabilities
Tools
The server offers five core tools:
Datapath Management Tools
get_switchesList all connected OpenFlow datapaths
No input required
Returns: Array of active POX-controlled switches
Includes connection status and capabilities
get_switch_descGet detailed datapath information
Input:
dpid(string): Datapath identifier
Returns: POX-managed switch details and features
Flow Management Tools
get_flow_statsRetrieve POX flow statistics
Input:
dpid(string): Datapath identifiermatch(object, optional): POX match structuretable_id(string, optional): OpenFlow table IDout_port(string, optional): Output port filter
Returns: POX flow statistics including packet counts
set_tableConfigure POX flow tables
Input:
dpid(string): Datapath identifierflows(array): POX flow specifications
Returns: Flow table update confirmation
Analysis Tools
append_insightAdd network insights to POX configuration memo
Input:
insight(string): Network observation or analysis
Returns: Insight addition confirmation
Updates pox://network-config resource
Usage with Claude Desktop
uv
{
"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"
}
}
}
}License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Contributing
Contributions are welcome! Please feel free to submit pull requests, report bugs, or suggest new features.
Available Tools
5 toolsappend_insightC
Add a network insight to the configuration memo
Inputs: insight (required).
get_flow_statsC
Get flow statistics from a switch
Inputs: dpid (required), match, table_id, out_port.
get_switch_descC
Get detailed information about a specific switch
Inputs: dpid (required).
get_switchesA
Get a list of all connected OpenFlow switches
Inputs: no named parameters.
set_tableC
Set the flow table on a switch
Inputs: dpid (required), flows (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct operation: listing switches, getting switch details, getting flow stats, setting the flow table, and appending an insight. No overlapping purposes.
All tool names follow a consistent verb_noun pattern in snake_case (append_insight, get_*, set_table), making them predictable and easy to understand.
With 5 tools, the server is well-scoped for its purpose of OpenFlow switch management. The number falls within the ideal range and each tool provides necessary functionality.
The set covers basic operations like querying and setting but lacks tools for deleting or modifying flow rules, or managing switch connections, leaving notable gaps for full lifecycle management.
Maintenance
Related MCP Connectors
The Google GKE MCP server is a managed Model Context Protocol server that provides AI applications with tools to manage Google Kubernetes Engine (GKE) clusters and Kubernetes resources. It exposes a structured, discoverable interface that allows AI agents to interact with GKE and Kubernetes APIs, enabling them to inspect cluster configurations, retrieve Kubernetes resource YAMLs, monitor operations like cluster upgrades, diagnose issues, and optimize costs—all without needing to parse text output or use complex kubectl commands.
The Telnyx MCP server is an official implementation of the Model Context Protocol that enables AI clients (like Claude Desktop, Cursor, and OpenAI Agents) to interact with Telnyx's telephony, messaging, and AI assistant APIs. It provides comprehensive capabilities including making and managing phone calls, sending SMS/MMS messages, purchasing and configuring phone numbers, creating AI assistants with custom instructions, managing cloud storage buckets, scraping and embedding website content, and handling integration secrets. The server exists as both a local implementation and a remotely hosted version, allowing developers to integrate real-world communication infrastructure directly into AI applications.
The OpenMesh MCP Server provides decentralized, permissionless cloud infrastructure that integrates AI assistants with Web2 and Web3 applications without middlemen. It offers intelligent service discovery to identify MCP servers, acts as a universal proxy for routing requests to discovered services, implements performance optimization through usage feedback, and provides automatic fault tolerance with alternative services when servers become unavailable.
The BigQuery remote MCP server is a fully managed service that uses the Model Context Protocol to connect AI applications and LLMs to BigQuery data sources. It provides secure, standardized tools for AI agents to list datasets and tables, retrieve schemas, generate and execute SQL queries through natural language, and analyze data—enabling direct access to enterprise analytics data without requiring manual SQL coding.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that provides programmatic access to ONOS SDN controller's network management capabilities, enabling device control, topology management, and analytics through ONOS's REST API.6GPL 3.0
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables management of F5 devices through natural language commands, allowing users to create, update, list, and delete network objects like virtual servers, pools, and iRules via the iControl REST API.13MIT
- FlicenseAqualityDmaintenanceA Model Context Protocol server that enables LLMs to manage network topologies, labs, nodes, and configurations in the EVE-NG network emulation platform through a standardized interface.2615-
- AlicenseAqualityDmaintenanceA Model Context Protocol server that provides network packet capture and analysis capabilities through Wireshark/tshark integration, enabling AI assistants to perform network security analysis and troubleshooting.436MIT