{"slug": "let-ai-explain-traceroute-with-the-laws-of-physics", "title": "Let AI Explain traceroute with the Laws of Physics", "summary": "A developer has open-sourced PacketVoyage, an Agent Skill and MCP server that transforms traceroute outputs into educational stories about physics, geography, and undersea cables. The tool uses physical laws and heuristics to explain latency jumps and hidden IATA codes, and can be integrated with AI agents like Claude via MCP.", "body_md": "I built and open-sourced **PacketVoyage**—an Agent Skill & MCP server that turns boring `traceroute`\n\noutputs into fascinating stories about physics, geography, and undersea cables.\n\nModel Context Protocol (MCP) Server & Agent Skill for educational network traceroute analysis, fiber-optic physics verification, and packet voyage storytelling.Zero external commercial APIs, zero bundled copyright data — pure physical laws and detective insight.\n\nPacketVoyage is built around two complementary layers designed specifically for AI-native workflows:\n\n```\n┌────────────────────────────────────────────────────────┐\n│                   AI Agent (LLM)                       │\n└──────────────┬──────────────────────────┬──────────────┘\n               │                          │\n               ▼                          ▼\n┌──────────────────────────────┐ ┌──────────────────────────────┐\n│       🧠 Agent Skill         │ │        🛠️ MCP Server         │\n│     (Knowledge / Playbook)   │ │    (Capabilities / Execution)│\n├──────────────────────────────┤ ├──────────────────────────────┤\n│ • Speed of Light in Fiber    │ │ • analyze_voyage_text        │\n│   (~0.67c, ~10ms / 1,000km)  │ │ • voyage_investigate         │\n│ • Control vs Data Plane math │ │ • run_protocol_experiment    │\n│ • Disproving GeoIP illusions │ │ • research_host              │\n│ • Decision Flow & Heuristics │ │ • list_known_iata_airports   │\n└──────────────────────────────┘ └──────────────────────────────┘\n```\n\nEver wondered what’s actually happening behind a trace like this?\n\n```\n     1  gateway (192.168.1.1)                 0.8 ms\n     2  * * *\n     3  ae-1.tokyo-hnd.bb.net (203.0.113.1)    2.1 ms\n     4  xe-0-0.sjc-core.bb.net (198.51.100.25) 88.5 ms\n     5  one.one.one.one (1.1.1.1)             88.7 ms\n```\n\nBehind these lines lies real-world physics:\n\n• The * * * at Hop 2 isn't packet loss: Normal traffic runs at line rate in hardware ASICs (Data Plane), while diagnostic ICMP responses are rate limited by router CPUs (Control Plane).\n\n• The +86ms jump: Light travels in silica glass fiber at ~200,000 km/s (~10 ms RTT per 1,000 km). Tokyo to Silicon Valley is ~8,300 km, so ~83 ms is the theoretical speed-of-light limit across the Pacific ocean floor.\n\n• Hidden IATA codes: Hostnames like tokyo-hnd (Haneda) and sjc-core (San Jose) reveal the subsea cable route (e.g., JUNO / PC-1).\n\nFor students and general engineers, understanding what happens inside traceroute can be difficult. Let’s have AI explain it instead.\n\n```\n  ### 🚢 Example AI Output\n\n  Feed that trace to Claude or any MCP-enabled AI agent by packetvoyage skill\n\n  │ 📍 Route: Tokyo (HND) 🌊 [JUNO Submarine Cable] ➔ San Jose (SJC) (~8,335 km)\n  │ 🌊 Physics Check: Latency spiked from 2.1 ms ➔ 88.5 ms (+86.4 ms), perfectly matching the speed of light in transpacific optical fiber. Hop 2\n  │ asterisks are standard CPU control-plane rate limiting.\n  ──────\n```\n\nAdd it to Claude Code with one command:\n\n```\nclaude mcp add packetvoyage -- uvx --from git+https://github.com/europeanplaice/packetvoyage.git packetvoyage\n```\n\nFor Claude Desktop / Cursor / Antigravity, add this to your MCP config:\n\n```\n{\n  \"mcpServers\": {\n    \"packetvoyage\": {\n      \"command\": \"uvx\",\n      \"args\": [\"--from\", \"git+https://github.com/europeanplaice/packetvoyage.git\", \"packetvoyage\"]\n    }\n  }\n}\n```\n\nCheck out the repo and give your next traceroute a physical voyage!\n\n👉 GitHub: europeanplaice/packetvoyage [https://github.com/europeanplaice/packetvoyage](https://github.com/europeanplaice/packetvoyage)", "url": "https://wpnews.pro/news/let-ai-explain-traceroute-with-the-laws-of-physics", "canonical_source": "https://dev.to/europeanplaice/let-ai-explain-traceroute-with-the-laws-of-physics-2ckh", "published_at": "2026-08-15 15:34:09+00:00", "updated_at": "2026-08-15 15:42:03.896510+00:00", "lang": "en", "topics": ["developer-tools", "ai-agents", "ai-tools"], "entities": ["PacketVoyage", "MCP", "Claude", "GitHub", "europeanplaice"], "alternates": {"html": "https://wpnews.pro/news/let-ai-explain-traceroute-with-the-laws-of-physics", "markdown": "https://wpnews.pro/news/let-ai-explain-traceroute-with-the-laws-of-physics.md", "text": "https://wpnews.pro/news/let-ai-explain-traceroute-with-the-laws-of-physics.txt", "jsonld": "https://wpnews.pro/news/let-ai-explain-traceroute-with-the-laws-of-physics.jsonld"}}