brainiall-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BRAINIALL_API_KEY | Yes | Your API key for Brainiall Speech AI, available at app.brainiall.com |
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 |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| assess_pronunciationA | Assess how accurately a speaker pronounced the given text. Returns an overall pronunciation score (0-100), per-word scores, and phoneme-level feedback including accuracy, fluency, and completeness. |
| transcribe_speechB | Transcribe speech audio into text. Supports multiple languages with automatic language detection. Returns the transcription text and detected language. |
| synthesize_speechA | Convert text to natural-sounding speech audio. Returns base64-encoded audio in MP3 format. Use list_voices to see available voice options. |
| list_voicesA | List all available text-to-speech voices. Returns voice IDs, names, supported languages, and sample previews. |
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 clearly distinct purpose with no overlap: assess_pronunciation evaluates speech quality, list_voices enumerates TTS options, synthesize_speech generates audio, and transcribe_speech converts audio to text. The descriptions clearly differentiate these functions, making misselection unlikely.
All tool names follow a consistent verb_noun pattern with snake_case (e.g., assess_pronunciation, synthesize_speech). The verbs (assess, list, synthesize, transcribe) are descriptive and aligned with the actions, creating a predictable and readable naming convention throughout.
With 4 tools, this server is well-scoped for speech and audio processing. Each tool earns its place by covering distinct aspects: pronunciation assessment, voice listing, speech synthesis, and transcription. This count is appropriate for the domain, avoiding bloat or thin coverage.
The tool set covers core speech processing workflows: synthesis, transcription, and pronunciation feedback. Minor gaps exist, such as no explicit tools for voice customization or audio editing, but agents can likely work around these with the provided tools. The surface is largely complete for the stated purpose.