AI agents call sstv_detect to retrieve information from Sensory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads and analyzes audio data to determine whether SSTV (Slow Scan Television) content is present, returning a boolean or detection result. This is a pure read operation—no data is created, modified, deleted, or executed. No external commands are triggered; no financial transactions occur.
From the tool's definition Tool description states 'Detect if audio contains an SSTV signal' — a detection/analysis operation with no side effects. This is the 'first step of REFLUX decode', indicating it performs signal analysis and retrieval of information from audio input.
Attacks that exploit this kind of access
Detect if audio contains an SSTV signal. First step of REFLUX decode. It is categorised as a Read tool in the Sensory MCP Server, which means it retrieves data without modifying state.
Register the Sensory MCP server in PolicyLayer and add a rule for sstv_detect: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Sensory. Nothing to install.
sstv_detect is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the sstv_detect rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for sstv_detect. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
sstv_detect is provided by the Sensory MCP server (jaspertvdm/mcp-server-sensory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →