speech_availability
Report whether this device supports on-device speech recognition. A true result is DEVICE capability only — NOT proof the caller is authorized: macOS gates transcription by Speech Recognition permission on the responsible process (the signed AirMCP app), so only a successful transcribe_audio conf...
This record as markdown: /tools/heznpc-airmcp/speech-availability.md
What speech_availability does on AirMCP
AI agents call speech_availability to retrieve information from AirMCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why speech_availability is rated Low
This tool performs a read-only capability check and does not modify, execute, delete, or financially impact any system. The description explicitly notes it is NOT proof of authorization and does not actually perform transcription. It is a simple informational query about device capabilities, making it a low-severity Read operation.
From the tool's definition The tool 'speech_availability' reports a device capability status — it 'Report[s] whether this device supports on-device speech recognition.' This is a query that retrieves system capability information with no side effects.
Attacks that exploit this kind of access
The rule that runs speech_availability safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AirMCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For speech_availability, this is the rule to start with:
speech_availability is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect AirMCP, apply this rule, and every speech_availability call is checked against it from then on.
Questions about speech_availability
Report whether this device supports on-device speech recognition. A true result is DEVICE capability only — NOT proof the caller is authorized: macOS gates transcription by Speech Recognition permission on the responsible process (the signed AirMCP app), so only a successful transcribe_audio confirms authorization. It is categorised as a Read tool in the AirMCP MCP Server, which means it retrieves data without modifying state.
Register the Air MCP server in PolicyLayer and add a rule for speech_availability: 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 AirMCP. Nothing to install.
speech_availability 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_availability 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_availability. 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_availability is provided by the Air MCP server (airmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Air, and thousands of servers like it.
This server
Across the catalogue