keenetic-mcpSAFE
Control any Keenetic router via AI agents — MCP server for managing devices, traffic, and settings in plain language.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
👨💻 keenetic-mcp - Control Your Keenetic Router With AI
⬇️ Download Keenetic-MCP
🤔 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 won’t mess up your network if you make a mistake.
🎯 Who Is This For?
You don’t need to be a programmer. If you can click a button and copy-paste text, you can set this up. It’s 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
📦 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 aren’t pre-canned scripts—the AI learns how your router behaves thro
1de4ae0a182eOBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add keenetic-mcp -- npx -y [email protected]
{
"mcpServers": {
"keenetic-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (20)
15 read · 4 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
Home | read | Home network |
Policy0 | read | desc-1 |
backup_config | read | |
create_segment | write | |
delete_segment | destructive | |
get_config_state | read | |
get_device | read | |
get_interface | read | |
get_internet_status | read | |
get_system_info | read | |
get_wifi_status | read | |
list_devices | read | |
list_interfaces | read | |
list_policies | read | |
list_routes | read | |
list_segments | read | |
rci_call | read | |
save_config | write | |
set_interface_state | write | |
update_device | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (10)
delete_segment
v1.5.zip
const md5 = createHash('md5').update(`${login}:${realm}:${password}`).digest('hex');const md5 = createHash('md5').update(`${LOGIN}:${REALM}:${PASSWORD}`).digest('hex');import { runInit, type InitDeps } from '../../src/cli/init.js';import { readStoredConfig } from '../../src/config/discover.js';} from '../../src/config/discover.js';
import { loadConfig } from '../../src/config/load.js';import { createSecretStore, keychainCommand, type Runner } from '../../src/config/secrets.js';zod, @modelcontextprotocol/client, @types/node, tsx, typescript, vitest
Gates applied: no_behavioural_pass.
1de4ae0a182efull audit observations/trust-audit/mcp-server/elihucredible450__keenetic-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 1de4ae0a182e | SAFE | B | 89 | first audit |
Questions
What is the keenetic-mcp MCP server?
Control any Keenetic router via AI agents — MCP server for managing devices, traffic, and settings in plain language.
What tools does keenetic-mcp expose?
20 in total: 15 read-only, 4 that write, and 1 that can delete or overwrite (delete_segment). Every one is listed on this page with its risk.
Is keenetic-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does keenetic-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does keenetic-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as keenetic-mcp at 0.0.0-dev.
How current is this page?
The grade is for one exact copy of the source (1de4ae0a182e), read on 2026-10-11. The repository is watched and re-audited when it changes.