cisco-open/network-sketcher

Network Sketcher is an AI-ready network design tool with Local MCP, Online, and Offline editions for creating network designs and exporting PowerPoint diagrams and Excel-based configuration data.

What it solves

Network Sketcher simplifies the process of designing and documenting network topologies. It eliminates the need for manual diagramming by automatically generating L1 (physical), L2 (VLAN/broadcast domain), and L3 (IP) topology diagrams and device tables from structured data or natural language descriptions.

How it works

The tool converts network data—either provided via structured files, CLI commands, or natural language prompts—into visual diagrams (SVG, PowerPoint) and tables (HTML, Excel). It offers three distinct editions:

  • Local MCP: An AI-native server using the Model Context Protocol (MCP) that allows LLM clients (like Cursor or Claude Code) to execute network design commands directly.
  • Online: A browser-based web service that allows users to interact with an LLM via copy-pasting AI context files and CLI commands.
  • Offline: A standalone desktop application with a GUI and CLI for manual management in Excel and PowerPoint.

It also integrates with a separate Cisco Extension to import live inventory from platforms like ACI, Meraki, and NetBox, converting them into compatible CLI scripts.

Who it’s for

Network engineers and architects who need to rapidly prototype, document, or review Cisco-style network designs using AI assistance.

Highlights

  • AI-Native Integration: Direct tool-calling via MCP for seamless design within AI agents.
  • Multi-Layer Visualization: Automatically generates L1, L2, and L3 diagrams.
  • Flexible Export Formats: Supports SVG, PowerPoint, draw.io (with Cisco stencils), and Excel.
  • Live Inventory Import: Converts data from various Cisco platforms and third-party tools into design scripts.
  • AI Context Generation: Creates specialized files that allow other LLMs to understand and extend the current network design.

Related

  • Project
    ahujasid/blender-mcp

    A bridge connecting Blender to LLMs via the Model Context Protocol, enabling prompt-assisted 3D modeling, scene creation, and asset manipulation.

  • Project
    DeusData/codebase-memory-mcp

    A native, zero‑runtime executable that builds a persistent, multi‑language knowledge graph of a codebase (158 languages) using Tree‑sitter and a custom “Hybrid LSP” type resolver. The graph can be queried instantly (structural, semantic, Cypher‑like) and is consumed by AI coding agents (Claude Code, Codex, OpenCode, etc.) to answer code‑understanding questions without sending source files to the cloud. Includes a built‑in 3D UI, cross‑repo linking, dead‑code detection, impact analysis, and integrates automatically with 43 supported agents. All processing is local, fast (Linux kernel indexed in ~3 min), and distributed via npm, PyPI, Homebrew, etc.

  • Project
    korotovsky/slack-mcp-server

    An MCP server that enables AI models to interact with Slack workspaces, allowing them to read, search, and manage messages, users, and channels.

  • Project
    Capsize-Games/airunner

    AI Runner is an offline‑first desktop app that bundles a local LLM, text‑to‑speech, speech‑to‑text, and Stable‑Diffusion image generators. It lets you create a personalized chat companion (name, voice, memory) and a layered drawing canvas where sketches can be turned into AI‑generated images. Everything runs locally, with built‑in model download tools, safety filters, and a headless REST API for scripting or VS Code integration.

  • Project
    arabold/docs-mcp-server

    Grounded Docs MCP Server is a local, version‑aware documentation indexer that scrapes official docs (web, GitHub, npm, PyPI, local files), converts them to searchable text, and optionally adds vector embeddings. It exposes a simple MCP (SSE) API so AI coding assistants (Claude, Cline, Copilot, Gemini‑CLI, etc.) can retrieve exact documentation passages, reducing hallucinations while keeping data private.