Schema | Voice Shield

Voice Shield

Describes the environment variables required to run the server.

Name	Required	Description
`SOURCE`	No	Audio source passed via the --source CLI flag: `file:demo.wav` to replay a clip, `mic` to listen through the laptop microphone (call on speakerphone), or `phone` for a live SIM call from a USB-connected Android device (scrcpy).
`PUBLIC_HOST`	No	Optional public hostname (e.g. <name>.trycloudflare.com) to expose the server over HTTPS for a remote MCP client. Restart the server with PUBLIC_HOST=<name>.trycloudflare.com after starting the tunnel. The server then runs in JSON-response, stateless mode.
`AWS_ACCESS_KEY_ID`	No	Optional AWS access key ID. When AWS credentials are provided, the words layer is routed through Amazon Bedrock Nova Micro instead of the offline keyword classifier. Only transcript text is sent, never audio.
`TELEGRAM_BOT_TOKEN`	No	Optional Telegram bot token used for family verification (the "Are you calling?" button on the real family member's phone). Without it, family verification is unavailable.
`AWS_SECRET_ACCESS_KEY`	No	Optional AWS secret access key, used together with AWS_ACCESS_KEY_ID for Bedrock Nova Micro.
`TELEGRAM_FAMILY_CHAT_ID`	No	Optional Telegram chat ID of the family member who receives the verification request. Used together with TELEGRAM_BOT_TOKEN.

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityMaintained

ResponsivenessNo issues