Turn text into speech with Nigerian and African-accented voices.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
List all available YarnGPT voices with names and descriptions. Use before text_to_speech when the user asks which voices exist or which voice to pick. Voices: Idera, Emma, Zainab, Osagie, Wura, Jude, Chinenye, Tayo, Regina, Femi, Adaora, Umar, Mary, Nonso, Remi, Adam.
Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http mcp-bgpt-yarngpt https://nova.civai.co/mcp/agents/mcp-bgpt-yarngpt
List all available YarnGPT voices with names and descriptions. Use before text_to_speech when the user asks which voices exist or which voice to pick. Voices: Idera, Emma, Zainab, Osagie, Wura, Jude, Chinenye, Tayo, Regina, Femi, Adaora, Umar, Mary, Nonso, Remi, Adam.
| Argument | Type | Description |
|---|---|---|
| notification_message | string | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
{
"type": "object",
"properties": {
"notification_message": {
"type": "string",
"description": "Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names."
}
}
}Convert text to speech with YarnGPT. Pass text (required, max 2000 characters) and voice (required). response_format defaults to mp3 (mp3, wav, opus, or flac). Use list_voices to discover voices. API key comes from global_variables.
| Argument | Type | Description |
|---|---|---|
| text* | string | The text to convert to speech. Max 2000 characters. |
| voice* | string | Voice character to use. One of: Idera, Emma, Zainab, Osagie, Wura, Jude, Chinenye, Tayo, Regina, Femi, Adaora, Umar, Mary, Nonso, Remi, Adam. Default Idera if unsure; call list_voices for descriptions. |
| notification_message | string | Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names. |
{
"type": "object",
"required": [
"text",
"voice"
],
"properties": {
"text": {
"type": "string",
"description": "The text to convert to speech. Max 2000 characters."
},
"voice": {
"type": "string",
"description": "Voice character to use. One of: Idera, Emma, Zainab, Osagie, Wura, Jude, Chinenye, Tayo, Regina, Femi, Adaora, Umar, Mary, Nonso, Remi, Adam. Default Idera if unsure; call list_voices for descriptions."
},
"notification_message": {
"type": "string",
"description": "Short user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 2, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.