mcp-server-sensory
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| morse_encodeB | Encode text to Morse code. Formats: standard (.-), visual (█▄), binary (10) |
| morse_decodeB | Decode Morse code back to text |
| morse_timingC | Get timing data for Morse audio/light generation |
| braille_encodeB | Encode text to Braille Unicode characters |
| braille_decodeC | Decode Braille back to text |
| braille_punchcardC | Generate ASCII punchcard pattern from text - can be physically punched for audit trail! |
| braille_binary_gridC | Generate binary grid for machine-readable punchcard or CNC/laser cutting |
| transcodeC | Convert between different sensory encodings |
| sstv_encode_textA | Encode text to SSTV audio (Robot36/Martin/Scottie). Returns base64 WAV. Multi-modal bridge for small LLMs! |
| sstv_encode_ponskaartB | Create authenticated ponskaart (punch card) for McMurdo remote authentication via SSTV |
| sstv_modesB | List available SSTV modes with their specifications |
| sstv_detectB | Detect if audio contains an SSTV signal. First step of REFLUX decode. |
| sstv_decoder_infoA | Get SSTV decoder capabilities and REFLUX readiness status |
| reflux_decodeB | Complete REFLUX decode: SSTV Audio → Image → OCR → Text. Gives small LLMs 'eyes' via audio! |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
Tools are mostly distinct by format and action, but 'braille_binary_grid' and 'braille_punchcard' both generate patterns with some overlap, and 'transcode' is vague. Overall, agents can usually differentiate.
Naming follows a consistent snake_case pattern and typically starts with the sensory type (e.g., braille_, morse_, sstv_), except for 'transcode' and 'reflux_decode'. The pattern is not strictly verb_noun but is predictable.
With 14 tools covering three sensory formats plus a transcode utility, the count is well-scoped and each tool serves a clear purpose. Not too few or too many.
The set covers Braille and Morse encoding/decoding well, but SSTV lacks a standalone decode tool (only a composite pipeline via reflux_decode). Other sensory formats are omitted, leaving minor gaps.