Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/elihucredible450/keenetic-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/elihucredible450/keenetic-mcp/setup)<a href="https://agentmods.dev/commands/elihucredible450/keenetic-mcp/setup"><img src="https://agentmods.dev/badge/commands/elihucredible450/keenetic-mcp/setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/elihucredible450/keenetic-mcp/setup"><img src="https://agentmods.dev/badge/commands/elihucredible450/keenetic-mcp/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00008 | $0.00436 |
| Opus 5 | $0.00004 | $0.00218 |
| Sonnet 5 | $0.00002 | $0.00087 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to setup — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
The user wants to connect the Keenetic MCP server to their router.
The server needs three things: the router address, a login, and a password. It finds the address itself and stores the password in the operating system keychain, so the only thing you have to do is walk the user through running the wizard.
Do not ask the user for their password and do not run the wizard yourself. It reads the password from the terminal without echoing it, which only works when the user runs it. Tell them to run this in their own terminal:
npx -y keenetic-mcp init
Explain what will happen, so nothing is a surprise:
- It reads the default gateway and offers it as the router address. Pressing enter accepts it.
- It confirms the address really is a Keenetic before asking for anything else.
- The login defaults to
admin. - The password is typed without being shown, and is checked against the router immediately. Nothing is stored if the router rejects it.
- The password goes into the system keychain. The settings file holds only the address and the login.
Once they say it finished, verify it by calling get_system_info. It should
return the model and firmware version. If it fails:
- "No router configured" means the wizard did not complete. Ask them to run it again and read out any message it printed.
- "the router rejected credentials" means the password is wrong. The router password is the one for its web interface, which is often not the Wi-Fi password.
- "The router was unreachable" means this machine is not on the same network as the router, or the address is wrong.
If the user would rather not store anything, the server also reads
KEENETIC_HOST, KEENETIC_USER and KEENETIC_PASSWORD from the environment,
and those take precedence over the stored settings.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 45 lines · 8 tokens per session scan A 6bd94304e344
setup is a command published in the GitHub repository elihucredible450/keenetic-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 8 tokens to every session and 436 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to setup, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
setup
Connect this plugin to your Keenetic router.
eol-report
EOL/EOS risk report — devices, OS versions, and firmware approaching or past end-of-life/end-of-support, prioritized by criticality.
brand-setup
Configure a new brand profile with colors, fonts, logo, visual style, platforms, and compliance rules.
screens
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.
rvcsi-calibrate
Learn a v0 per-subcarrier baseline (mean amplitude) from a .rvcsi capture.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.