Let AI Explain traceroute with the Laws of Physics

I built and open-sourced PacketVoyage—an Agent Skill & MCP server that turns boring traceroute outputs into fascinating stories about physics, geography, and undersea cables.

europeanplaice / packetvoyage

MCP server & Agent Skill for educational network traceroute analysis, fiber-optic physics verification, and packet voyage storytelling

🚢 PacketVoyage

Model 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.

---

🏛️ Architecture: The Two Pillars

PacketVoyage is built around two complementary layers designed specifically for AI-native workflows:

┌────────────────────────────────────────────────────────┐
│                   AI Agent (LLM)                       │
└──────────────┬──────────────────────────┬──────────────┘
               │                          │
               ▼                          ▼
┌──────────────────────────────┐ ┌──────────────────────────────┐
│       🧠 Agent Skill         │ │        🛠️ MCP Server         │
│     (Knowledge / Playbook)   │ │    (Capabilities / Execution)│
├──────────────────────────────┤ ├──────────────────────────────┤
│ • Speed of Light in Fiber    │ │ • analyze_voyage_text        │
│   (~0.67c, ~10ms / 1,000km)  │ │ • voyage_investigate         │
│ • Control vs Data Plane math │ │ • run_protocol_experiment    │
│ • Disproving GeoIP illusions │ │ • research_host              │
│ • Decision Flow & Heuristics │ │ • list_known_iata_airports   │
└──────────────────────────────┘ └──────────────────────────────┘

1. 🛠️ MCP Server (Capabilities &…

View on GitHub

Ever wondered what’s actually happening behind a trace like this?

     1  gateway (192.168.1.1)                 0.8 ms
     2  * * *
     3  ae-1.tokyo-hnd.bb.net (203.0.113.1)    2.1 ms
     4  xe-0-0.sjc-core.bb.net (198.51.100.25) 88.5 ms
     5  one.one.one.one (1.1.1.1)             88.7 ms

Behind these lines lies real-world physics:

• 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).
• 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.
• Hidden IATA codes: Hostnames like tokyo-hnd (Haneda) and sjc-core (San Jose) reveal the subsea cable route (e.g., JUNO / PC-1).

For students and general engineers, understanding what happens inside traceroute can be difficult. Let’s have AI explain it instead.

  ### 🚢 Example AI Output

  Feed that trace to Claude or any MCP-enabled AI agent by packetvoyage skill

  │ 📍 Route: Tokyo (HND) 🌊 [JUNO Submarine Cable] ➔ San Jose (SJC) (~8,335 km)
  │ 🌊 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
  │ asterisks are standard CPU control-plane rate limiting.
  ──────

🚀 Quickstart

Add it to Claude Code with one command:

claude mcp add packetvoyage -- uvx --from git+https://github.com/europeanplaice/packetvoyage.git packetvoyage

For Claude Desktop / Cursor / Antigravity, add this to your MCP config:

{
  "mcpServers": {
    "packetvoyage": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/europeanplaice/packetvoyage.git", "packetvoyage"]
    }
  }
}

Check out the repo and give your next traceroute a physical voyage!
👉 GitHub: europeanplaice/packetvoyage https://github.com/europeanplaice/packetvoyage