Mikrotik Harness banner
vesslina vesslina

Mikrotik Harness

AI community

Description

MikroTik Harness - AI Agents A tool designed to configure MikroTik hardware using the LLM Agent, add your OpenAI compatible API keys or use local models via LM Studio.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

MikroTik Harness

MikroTik Harness

A keyboard-first RouterOS workspace for LLM agents.

version 0.1.0 MIT license Windows 10 or 11 Python 3.11 or 3.12 Node.js 22 or newer RouterOS 7.x MikroMCP v1.10.0

[Русская версия](README_RU.md)

MikroTik Harness (`mth`) is a community CLI project that gives an LLM agent a practical, mode-controlled workspace for MikroTik RouterOS. It discovers a router, connects a model, exposes the appropriate tools, records the session, and keeps the operator in control of changes.

The typed RouterOS backend comes from [MikroMCP](https://github.com/AliKarami/MikroMCP) ([official site](https://mikromcp.com/)). `mth` runs the pinned backend locally and adds discovery, model providers, permissions, approvals, session history, offline RouterOS reference search, and a persistent HIGH RISK SSH channel.

[!WARNING] This is not an official MikroTik product. Test changes on a lab device first. HIGH RISK can make any change the connected RouterOS user is allowed to make.

What it does

  • Discovers MikroTik devices over MNDP or connects to a manually entered address.
  • Works with LM Studio, Ollama, and arbitrary OpenAI-compatible chat-completions endpoints.
  • Gives the model different RouterOS authority in PLAN, READY, and HIGH RISK modes.
  • Uses