Sandbox
@jeff-nasseri/mikrotik-mcp

MCP server for MikroTik RouterOS devices

MikroTik MCP sits between an MCP client and MikroTik RouterOS so your assistant can issue router commands through natural language. The project includes the server code, tests, setup docs, and examples for single-device and inventory-based device management.

268 starsβ€’57 forksβ€’Pythonβ€’Updated 15d ago
Who it's for

Builders who want an MCP client to manage MikroTik routers and fleets from chat.

What it delivers

You can ask your assistant to inspect and change MikroTik network settings without switching to RouterOS by hand.

What it does

RouterOS actions through MCP

Lets an AI assistant send RouterOS management requests through the MCP server.

Network configuration tasks

Supports router work such as VLANs, firewall rules, DNS settings, and related management commands.

Multiple-device inventory

Includes inventory support for managing more than one MikroTik device in a fleet structure.

Client integration guides

Provides setup docs for Claude Desktop, MCP Inspector, and other MCP clients.

Docker-based local setup

Includes Docker files and a `routeros-docker` example for running the server and test environment.

README

MikroTik MCP

MCP Toplist

MseeP.ai Security Assessment Badge

Website Build Status Tests MIT License

Overview

MikroTik MCP provides a bridge between AI assistants and MikroTik RouterOS devices. It allows AI assistants to interact with MikroTik routers through natural language requests, executing commands like managing VLANs, configuring firewall rules, handling DNS settings, and more.

Demo Videos

Claude Desktop

https://github.com/user-attachments/assets/24fadcdc-c6a8-48ed-90ac-74baf8f94b59

Inspector

https://github.com/user-attachments/assets/e0301ff2-8144-4503-83d0-48589d95027d

Inventory

[!NOTE] Since MikroTik MCP version 0.14.0, the MikroTik MCP will allow you to manage multiple MikroTik devices within your fleet structure. The following video simply shows how to use the inventory of MikroTik devices to let LLMs talk with your MikroTik devices.

https://github.com/user-attachments/assets/185b2c39-8f55-4f26-a74c-2ac459ad38f5

Documentation

πŸ“š Full Documentation - Complete guides, API reference, and examples

🌐 Prefer to read online? The same documentation is also published at www.mikrotik-mcp.com (docs) β€” an optional, web-friendly way to explore the project while reviewing the repo.

Quick Links

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.

Files in the repo

Repository payloadβ€’22 top-level entries
  • .github
  • docs
  • routeros-docker
  • src
  • tests
  • .dockerignore
  • .gitattributes
  • .gitignore
  • conftest.py
  • CONTRIBUTING.md
  • docker-entrypoint.sh
  • Dockerfile
  • GitVersion.yml
  • inventory.example.yml
  • LICENSE
  • mcp-config.json.example
  • pyproject.toml
  • pytest.ini
  • README.md
  • requirements.txt
  • SECURITY.md
  • server.json

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph β€” average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code β€” use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300Β΅s in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up β€” it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k