earshot-relay MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EARSHOT_API_URL | Yes | The base URL of the earshot-relay server (e.g., http://127.0.0.1:8080). | |
| EARSHOT_API_TOKEN | Yes | The bearer token for authenticating to the earshot-relay API (same as EARSHOT_RELAY_TOKEN). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Earshot reads text aloud on the user's Android phone: the relay stores a message in the user's own bucket and the Earshot app, when it is listening, plays it. A successful send means stored, not heard. Keep spoken text short and plain: one or two sentences, no markdown, code, URLs or long lists. Never put secrets, passwords, tokens or private data in spoken text: it is stored in the bucket and spoken out loud. Use alarm (when present) only for urgency the user asked for. A receipt records what the phone did (device playback), not proof that a person heard it.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| sayA | Send a short message to be spoken aloud on the user's phone through Earshot. The text is stored in the user's bucket; if the Earshot app is listening it should speak it within seconds (Android text-to-speech by default, at the phone's media volume; held while the phone is on a call). A successful call means stored, not played. Keep it to one or two plain sentences. Returns the message id; call receipt with it to learn whether the phone played it. Not for the alarm channel: urgent alerts use the alarm tool, which exists only when the user enabled it. |
| receiptA | Did the phone play it? Returns the device-playback receipt of a message (id from say or alarm, or 'latest'): stored, detected, started, finished, skipped (the user skipped it), failed, missed (not played: it went stale, the bucket changed or audio was unavailable) or unconfirmed (no device report yet). wait_seconds (0-60) waits for a final status; |
| recentB | List recent messages sent through this relay with their playback status (newest first). |
| statusA | Relay status: sendable channels, speech modes, and the last beacon from each phone. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a distinct role: say sends, receipt checks a specific message's playback, recent lists history, and status reports relay state. The main confusion is that say's description points to an 'alarm tool' for urgent alerts that does not exist in this tool set, and receipt's status vocabulary overlaps with recent's playback status listing.
All names are single lowercase words, which is at least consistent in style, but the parts of speech vary (verb 'say' vs. nouns 'receipt'/'status' vs. adjective 'recent'). There is no predictable verb_noun pattern that would help an agent infer new tool names.
Four tools is a tight, well-scoped set for a message relay: send, verify, list, and health. It is on the thin side, and the missing alarm channel referenced in descriptions suggests the surface was trimmed.
The say description explicitly defers urgent alerts to an 'alarm tool' that is absent, creating a dead end for the server's stated urgent-use case. There is also no way to cancel a message, inspect bucket contents, or manage which phones are registered, leaving only the happy path covered.