EarSay MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
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.
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| voice_startA | Start the EarSay transcription server if not already running. Call this once before using any other voice_* tools. If the server is already running, this is a no-op. |
| voice_stopA | Stop the EarSay transcription server and release the microphone. |
| voice_pauseA | Pause transcription. The microphone is released but the server stays alive. Call voice_resume to start listening again. |
| voice_resumeA | Resume transcription after a pause. The microphone is re-opened. |
| voice_get_textA | Get all transcribed text since the server started. Returns the complete transcript buffer. |
| voice_get_newA | Get text transcribed since the last checkpoint. Returns the new text and its potential checkpoint index. Use voice_set_checkpoint to mark what you've already read. |
| voice_set_checkpointA | Set a checkpoint at the given character position. This marks all text up to char_position as 'read'. Subsequent calls to voice_get_new will only return text after this position. Args: char_position: Character position in the transcript buffer (1-indexed). Must be after the last checkpoint and not exceed the total available text. |
| voice_statusA | Get the current status of the EarSay server. Returns status (listening/paused/stopped), uptime, character count, checkpoint count, and subscription count. |
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 8 tools
Each tool targets a distinct action on the transcription service: lifecycle (start/stop/pause/resume), retrieval (full vs. incremental), checkpointing, and status. The only potential overlap between voice_get_new and voice_get_text is clearly resolved by their descriptions (incremental since checkpoint vs. all text). No two tools perform the same operation.
All tool names follow the voice_<action> pattern using snake_case consistently. Actions are clear verbs or verb-noun combinations (get_new, set_checkpoint, start, stop, pause, resume). This uniformity makes the set predictable and easy to navigate.
With 8 tools, the set is well-scoped for a transcription server. Each tool fulfills a necessary role in the lifecycle, from initialization to text retrieval and checkpoint management. No tool is redundant or extraneous.
The tool surface covers the full lifecycle: start/stop, pause/resume, full and incremental text retrieval, checkpoint setting, and status monitoring. This provides all essential operations for interacting with the EarSay transcription server, with no obvious gaps that would hinder typical workflows.