// SCAN REPORT

Sensory

14 tools. 3 can modify or destroy data without limits.

3 write tools that can modify data. Rate limits recommended.

Last updated: 3 Jul 2026

3 can modify or destroy data

11 read-only

14 tools total

Community server · catalogue entry verified 03/07/2026

How to control Sensory ↓

TOOL MAP

What Sensory exposes to your agents

Read (11) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Sensory tools

Execute · Medium sstv_encode_text This tool actively processes input text and generates audio output (base64-encoded WAV file), triggering an encoding/signal-generation operation. Execute · Medium transcode This tool executes a conversion/transcoding process between sensory encoding formats. Write · Medium sstv_encode_ponskaart The tool creates (generates/produces) an authenticated punch card artifact used for remote authentication.

3 of Sensory's 14 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Sensory

PolicyLayer is an MCP gateway — it sits between your AI agents and Sensory, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "sstv_encode_ponskaart": {
    "limits": [
      {
        "counter": "sstv_encode_ponskaart_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "braille_binary_grid": {
    "limits": [
      {
        "counter": "braille_binary_grid_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Sensory — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON SENSORY →

Instant setup, no code required.

FULL CATALOGUE

All 14 Sensory tools

EXECUTE 2 tools

Execute sstv_encode_text Encode text to SSTV audio (Robot36/Martin/Scottie). Returns base64 WAV. Multi-modal bridge for small LLMs! Execute transcode Convert between different sensory encodings

WRITE 1 tools

Write sstv_encode_ponskaart Create authenticated ponskaart (punch card) for McMurdo remote authentication via SSTV

READ 11 tools

Read braille_binary_grid Generate binary grid for machine-readable punchcard or CNC/laser cutting Read braille_decode Decode Braille back to text Read braille_encode Encode text to Braille Unicode characters Read braille_punchcard Generate ASCII punchcard pattern from text - can be physically punched for audit trail! Read morse_decode Decode Morse code back to text Read morse_encode Encode text to Morse code. Formats: standard (.-), visual (█▄), binary (10) Read morse_timing Get timing data for Morse audio/light generation Read reflux_decode Complete REFLUX decode: SSTV Audio → Image → OCR → Text. Gives small LLMs Read sstv_decoder_info Get SSTV decoder capabilities and REFLUX readiness status Read sstv_detect Detect if audio contains an SSTV signal. First step of REFLUX decode. Read sstv_modes List available SSTV modes with their specifications

FAQ

Questions about Sensory

How do I prevent bulk modifications through Sensory? +

The Sensory server has 1 write tools including sstv_encode_ponskaart. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Sensory.

How many tools does the Sensory MCP server expose? +

14 tools across 2 categories: Read, Write. 11 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Sensory? +

Register the Sensory MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Sensory tool call.

Deterministic rules across all 14 Sensory tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SENSORY →

Instant setup, no code required.

14 Sensory tools catalogued and risk-classified — across an index of 43,000+ MCP servers.