mcp-speak
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 |
|---|---|
| speakA | Speaks the provided message aloud using neural Voice Design or macOS say. Blocking: waits until playback has completely finished before returning. |
| speak_non_blockingA | Speaks the provided message aloud using neural Voice Design or macOS say. Non-blocking: queues the message immediately and returns. Guarantees subsequent messages will be queued sequentially and not talk over each other. |
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 2 tools
The two tools perform the same core action but are clearly differentiated by blocking behavior, with descriptive names and explicit notes in the descriptions. There is some overlap in purpose, but the distinction is obvious enough for an agent to select correctly.
Both tool names follow a consistent verb-first pattern with a modifier suffix (speak, speak_non_blocking). Naming clearly conveys the difference without mixing conventions or vague verbs.
Two tools is well-scoped for a text-to-speech server with blocking and non-blocking variants. Every tool earns its place, and the count matches the narrow purpose.
The server provides both blocking and non-blocking speech synthesis, covering the primary use cases. Minor gaps like canceling playback or selecting voices exist, but they are optional for the core domain.