Convert speech to text using Whissle API
AI agents call speech_to_text to retrieve information from Whissle MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Speech-to-text conversion is fundamentally a read operation: it processes input (audio) and returns output (text transcription) with no side effects, no data modification, no code execution, and no irreversible actions. The API call is deterministic and safe. Severity is low because misuse would only expose the transcribed text content, not enable harmful external actions or data destruction.
From the tool's definition Tool description states 'Convert speech to text using Whissle API' — a one-way data conversion operation that retrieves/extracts text from audio input without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Convert speech to text using Whissle API. It is categorised as a Read tool in the Whissle MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Whissle MCP Server MCP server in PolicyLayer and add a rule for speech_to_text: 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 Whissle MCP Server. Nothing to install.
speech_to_text 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 speech_to_text 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 speech_to_text. 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.
speech_to_text is provided by the Whissle MCP Server MCP server (whissleai/whissle-mcp). 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 →