livechat-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LIVECHAT_DEBUG | No | Set to '1' for VAD/segmentation debug logs to stderr. | |
| LIVECHAT_END_PHRASE | No | Spoken phrase to end the voice session. | terminate voice session now |
| LIVECHAT_SILENCE_SEC | No | Silence duration after speech to end an utterance (seconds). | 1.5 |
| LIVECHAT_LONG_POLL_SEC | No | How long get_voice_input blocks before returning __NO_INPUT__ (seconds). | 300 |
| LIVECHAT_VAD_THRESHOLD | No | Silero VAD speech probability threshold. | 0.5 |
| LIVECHAT_WHISPER_MODEL | No | Whisper model size: tiny.en, base.en, small.en, medium.en, or tiny, base, small, medium (multilingual). | base.en |
| LIVECHAT_WHISPER_DEVICE | No | Device for Whisper: cpu, cuda, or auto. | auto |
| LIVECHAT_WHISPER_COMPUTE | No | Compute type for Whisper: int8 (CPU) or float16 (GPU). | int8 |
| LIVECHAT_WHISPER_LANGUAGE | No | Language code for Whisper (en, pt, es, ...) or auto to detect per utterance. | en |
| LIVECHAT_MAX_UTTERANCE_SEC | No | Maximum utterance length in seconds (force-cut runaway utterances). | 120 |
| LIVECHAT_MIN_UTTERANCE_SEC | No | Minimum utterance length in seconds (filters coughs). | 0.4 |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_voice_inputA | Returns the next voice utterance from the user as text. Used in a loop during voice review sessions. If multiple utterances are queued, they are joined with ' / '. Returns the literal string 'END_SESSION' when the user has ended the session (Ctrl+C, /endlivechat, or wake phrase) — stop calling this tool when you see that. Returns 'NO_INPUT' if the long-poll timed out with no speech; in that case, call this tool again. Returns 'ALREADY_RUNNING:' if another livechat MCP process (e.g. another Claude Code window) currently holds the session lock — ask the user to confirm a takeover, then call take_over_voice_session if they agree. |
| end_voice_sessionA | Cleanly end the current voice session. After calling this, any further get_voice_input calls will return 'END_SESSION'. Use this when the user invokes /endlivechat or otherwise asks to stop voice mode. |
| take_over_voice_sessionA | Forcibly take the cross-process session lock from another livechat MCP instance. Signals the holder to release, waits briefly, and starts a new session here. Only call this after the user explicitly confirms taking over from the other window. Returns 'OK' on success or an error string on failure. |
| reset_voice_sessionA | Clear stale shutdown state from a previous /endlivechat in this same MCP server process so a new voice session can start cleanly. Call this once at the very beginning of a /livechat session, after the announcement and before the first get_voice_input. Safe to call mid-session: if a session is already running healthily this is a no-op and no in-flight utterances are dropped. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| livechat | Start a live voice review session. Speak instead of typing. |
| endlivechat | End the active live voice session and summarize. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: retrieving input, ending the session, taking over a lock, and resetting state. No overlap or ambiguity between them.
All tool names follow a consistent verb_noun snake_case pattern (e.g., get_voice_input, end_voice_session). The pattern is uniform and predictable.
Four tools is well-scoped for a voice session lifecycle. Each tool serves a necessary function with no redundancy, fitting the server's narrow purpose.
The tool surface covers the full voice session lifecycle: starting clean, retrieving input, ending, and handling cross-process takeover. No obvious dead ends or missing operations for the intended use case.