AI agents call morse_timing 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 retrieves timing metadata needed to generate Morse code output. It performs no state changes, executes no external commands, and has no destructive or financial impact. The data returned is purely informational and used by other encoding tools downstream. Misuse poses minimal risk—an attacker could only retrieve timing specifications, not execute arbitrary code or cause harm.
From the tool's definition Tool name 'morse_timing' and description 'Get timing data for Morse audio/light generation' indicate retrieval of timing parameters. The verb 'Get' and lack of any modification, execution, or deletion language confirm read-only behavior.
Attacks that exploit this kind of access
Get timing data for Morse audio/light generation. 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 morse_timing: 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.
morse_timing 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 morse_timing 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 morse_timing. 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.
morse_timing 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 →