mcp-speak-when-done
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FASTMCP_PORT | No | Port for SSE server (default 8000) | |
| SPEECH_MODEL | No | TTS model (default auto-detected) | |
| SPEECH_SPEED | No | Speech speed (default 1.0) | |
| SPEECH_VOICE | No | Voice name (default auto-detected) | |
| OPENAI_API_KEY | No | API key for TTS provider (OpenAI or Groq) | |
| SPEECH_API_URL | No | API endpoint (default auto-detected) | |
| SPEECH_TIMEOUT | No | Request timeout in seconds (default 30) | |
| SPEECH_PROXY_URL | No | URL of remote SSE server | |
| SPEECH_MAX_RETRIES | No | Retry count (default 3) | |
| SPEECH_PROXY_TIMEOUT | No | Proxy timeout in seconds (default 10) |
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 |
|---|---|
| speak_when_doneA | Speak a brief summary of your response out loud. Call this at the end of EVERY response. Summarize what you said in 1-3 short sentences — shorter is better. If your response is a question, speak the question only, not the suggested answers. Keep it natural and conversational. |
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 1 tool
Only one tool exists, so there is no possibility of confusion or overlap between tools.
The single tool name 'speak_when_done' is clear, descriptive, and follows a natural verb_temporal pattern.
The server is narrowly scoped to speaking a summary when done, so one tool is perfectly appropriate and not thin.
The tool fully covers the server's stated purpose of providing a spoken summary; no additional tools are needed.