AI agents call sstv_modes 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.
This tool queries and returns information about available SSTV (Slow Scan Television) transmission modes and their technical specifications. It performs no data modifications, deletions, code execution, or external operations—it is a pure read operation that retrieves metadata. The blast radius of misuse is minimal, as incorrect use would only result in retrieving unwanted or irrelevant mode information.
From the tool's definition Tool name 'sstv_modes' and description 'List available SSTV modes with their specifications' indicate a retrieval operation that returns static configuration data without any side effects.
Attacks that exploit this kind of access
List available SSTV modes with their specifications. 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_modes: 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_modes 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_modes 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_modes. 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_modes 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 →