Skip to main content

Multi-Sensory AI Communication - Morse, Braille, SSTV/REFLUX encoding for off-grid AI networks. 'Een 7B model krijgt opeens ogen'

Project description

MCP Server Sensory

Multi-Sensory AI Communication for Off-Grid Networks

Part of the HumoticaOS McMurdo Off-Grid Communication Layer.

The Vision

Make non-multimodal AI models "multi-sensitive" by encoding data across different sensory channels:

┌─────────────────────────────────────────────────────────────┐
│                     YOUR MESSAGE                            │
└─────────────────────────┬───────────────────────────────────┘
                          │
        ┌─────────────────┼─────────────────┐
        ↓                 ↓                 ↓
   ┌─────────┐      ┌──────────┐      ┌──────────┐
   │  MORSE  │      │  BRAILLE │      │  SSTV*   │
   │  .--.   │      │  ⠓⠑⠇⠇⠕  │      │  [IMG]   │
   └────┬────┘      └────┬─────┘      └────┬─────┘
        ↓                ↓                 ↓
     AUDIO           VISUAL            AUDIO
     LIGHT          TACTILE           IMAGES
     VISUAL        PUNCHCARD          RADIO

*SSTV support coming soon (Robot36, Scottie, Martin modes)

Installation

pip install mcp-server-sensory

With audio support:

pip install mcp-server-sensory[audio]

Full installation (all features):

pip install mcp-server-sensory[full]

Features

Morse Code

  • Encode/decode text to Morse
  • Multiple output formats: standard (.-), visual (█▄), binary (10)
  • Timing data for audio/light generation
  • Embeddable in images for visual transmission

Braille

  • Encode/decode text to Braille Unicode
  • Generate punchcard patterns (ASCII art)
  • Binary grid output for CNC/laser cutting
  • Physical audit trail - punch into paper/card!

Coming Soon

  • ggwave - Ultrasonic data transmission (inaudible to humans)
  • SSTV - Robot36, Scottie, Martin image modes
  • RTTY - Classic radio teletype

Usage

As MCP Server

{
  "mcpServers": {
    "sensory": {
      "command": "mcp-server-sensory"
    }
  }
}

As Python Library

from mcp_server_sensory import morse, braille

# Morse encoding
message = morse.encode("HELLO")
print(message)  # .... . .-.. .-.. ---

# Visual Morse (for images)
visual = morse.encode("SOS", morse.MorseFormat.VISUAL)
print(visual)  # ▄▄▄ ███ ▄▄▄

# Braille encoding
braille_msg = braille.encode("hello")
print(braille_msg)  # ⠓⠑⠇⠇⠕

# Punchcard pattern (for physical encoding)
pattern = braille.to_punchcard_pattern("hello")
print(pattern)
# ●○ ●○ ●○ ●○ ●○
# ●○ ○○ ●○ ●○ ●○
# ○○ ○○ ●○ ●○ ○○

# Binary grid (for CNC/laser)
grid = braille.to_binary_grid("hi")
print(grid)
# [[1, 0, 0, 1, 0], [1, 0, 0, 1, 0], [0, 0, 0, 0, 0]]

Use Cases

Off-Grid AI Communication

Two Raspberry Pi's with speakers/mics can exchange messages via Morse audio - no internet required!

Physical Audit Trail (TIBET Integration)

Encode TIBET tokens as Braille punchcards. Physical, tamper-evident, human and machine readable.

Radio Communication

Ham radio operators can relay AI messages using Morse code or SSTV images.

Accessibility

Braille output enables tactile reading of AI responses.

Stealth Communication

ggwave ultrasonic mode transmits data above human hearing range.

The Stack

┌─────────────────────────────────────┐
│  mcp-server-sensory                 │
│  (Morse, Braille, SSTV, ggwave)     │
├─────────────────────────────────────┤
│  I-Poll (AI messaging)              │
├─────────────────────────────────────┤
│  AINS (agent discovery)             │
├─────────────────────────────────────┤
│  TIBET (trust & provenance)         │
└─────────────────────────────────────┘

Part of HumoticaOS

McMurdo Off-Grid Communication Layer

One love, one fAmIly! 💙

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_server_sensory-0.2.0.tar.gz (11.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_server_sensory-0.2.0-py3-none-any.whl (14.9 kB view details)

Uploaded Python 3

File details

Details for the file mcp_server_sensory-0.2.0.tar.gz.

File metadata

  • Download URL: mcp_server_sensory-0.2.0.tar.gz
  • Upload date:
  • Size: 11.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for mcp_server_sensory-0.2.0.tar.gz
Algorithm Hash digest
SHA256 d52f58bcd3426fed03a68759e92e584c13c943ee7b61ca33c30f58edde4772d1
MD5 17b8481dc2b942317221608ad2eb6bbe
BLAKE2b-256 209666960930e749bc0d1b823eff4658e0d591ed81d888f6f17fefc1402cdf97

See more details on using hashes here.

File details

Details for the file mcp_server_sensory-0.2.0-py3-none-any.whl.

File metadata

File hashes

Hashes for mcp_server_sensory-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 26409419cb90d56efecda46a546c1194f18cb6283652555e4b6f81721408e8bb
MD5 259748327ada88c4df72fafab6074e11
BLAKE2b-256 3309660ecb51cc7f82e6ad57014296dc90af0116306f879f1982169a8ec1ea01

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page