ai
ElevenLabs MCP Integration for Vercel AI SDK
Connect ElevenLabs to Vercel AI SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.
Connect ElevenLabs to Vercel AI SDK
Use KosmoKrator as a local integration gateway for Vercel AI SDK agents and scripts.
Create an MCP client that starts or connects to the KosmoKrator gateway for the selected integration. The gateway is local, scoped to this integration, and starts with
--write=deny so Vercel AI SDK can inspect read-capable tools without receiving write access by default.
ElevenLabs MCP Config for Vercel AI SDK
Prefer CLI JSON calls when a workflow only needs one deterministic integration operation.
{
"mcpServers": {
"kosmokrator-elevenlabs": {
"type": "stdio",
"command": "kosmo",
"args": [
"mcp:serve",
"--integration=elevenlabs",
"--write=deny"
]
}
}
} Run the Gateway Manually
kosmokrator mcp:serve --integration=elevenlabs --write=deny Why Use KosmoKrator Here
Expose only ElevenLabs instead of a broad multi-service tool list.
Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.
Start read-only, then opt into ask or allow for trusted workspaces.
ElevenLabs Tools Visible to Vercel AI SDK
Vercel AI SDK sees stable MCP tool names generated from the ElevenLabs integration catalog.
| MCP tool | Source function | Type | Description |
|---|---|---|---|
integration__elevenlabs__elevenlabs_text_to_speech | elevenlabs.elevenlabs_text_to_speech | Write | Convert text to speech audio using an ElevenLabs voice. Returns base64-encoded audio. Choose a voice ID and model ID to control the output. |
integration__elevenlabs__elevenlabs_list_voices | elevenlabs.elevenlabs_list_voices | Read | List all available voices in your ElevenLabs account, including pre-made and cloned voices. Use this to discover voice IDs for text-to-speech. |
integration__elevenlabs__elevenlabs_get_voice | elevenlabs.elevenlabs_get_voice | Read | Get detailed information about a specific ElevenLabs voice, including its settings, labels, and fine-tuning info. |
integration__elevenlabs__elevenlabs_create_voice | elevenlabs.elevenlabs_create_voice | Write | Create a new voice clone in ElevenLabs. Provide a name, optional audio sample file paths or base64-encoded data, and an optional description. |
integration__elevenlabs__elevenlabs_delete_voice | elevenlabs.elevenlabs_delete_voice | Write | Permanently delete a voice from your ElevenLabs account. This action cannot be undone. |
integration__elevenlabs__elevenlabs_get_models | elevenlabs.elevenlabs_get_models | Read | List all available ElevenLabs text-to-speech models, including their IDs, names, and language support. Use model IDs when calling text_to_speech. |
integration__elevenlabs__elevenlabs_get_history | elevenlabs.elevenlabs_get_history | Read | Browse your ElevenLabs generation history. Returns a paginated list of past text-to-speech requests with metadata. |
integration__elevenlabs__elevenlabs_get_current_user | elevenlabs.elevenlabs_get_current_user | Read | Get your ElevenLabs account details, including subscription tier, character usage, and remaining quota. |