voice.provider error?

[KikeVen]

I just installed the MCP server; it does connect, but I got an error. It might be hallucinating the cause and effect, but there is something wrong.

Based on the current tools available from the Vapi MCP server, no, you cannot create a new assistant at this moment.

While I can see tools to list and get assistants (mcp_vapi-mcp_list_assistants, mcp_vapi-mcp_get_assistant), the create_assistant tool is missing from my available toolset.

Why is it missing?
The error log in your active file (Untitled-1) explains why the tool failed to load. The create_assistant tool definition has an invalid JSON schema:

Array has duplicate items. (at /properties/voice/properties/provider/enum)

In the voice.provider enum list, "11labs" appears twice:
["vapi", "11labs", "azure", ..., "deepgram", "11labs", ...]

Because of this duplicate value, the MCP server likely rejected the tool definition, making it unavailable for use. You would need to fix this schema error in the MCP server configuration (removing the duplicate "11labs") and restart the server to make the create_assistant tool available.

The actual invalid returned messge

Tool `create_assistant` has invalid JSON parameters:
	- Array has duplicate items. (at /properties/voice/properties/provider/enum)
	- Schema: {"type":"object","properties":{"name":{"type":"string","description":"Name of the assistant"},"instructions":{"type":"string","default":"You are a helpful assistant.","description":"Instructions for the assistant"},"llm":{"anyOf":[{"anyOf":[{"type":"object","properties":{"provider":{"type":"string","const":"openai"},"model":{"type":"string","enum":["gpt-4o","gpt-4o-mini"]}},"required":["provider","model"],"additionalProperties":false},{"type":"object","properties":{"provider":{"type":"string","const":"anthropic"},"model":{"type":"string","enum":["claude-3-7-sonnet-20250219","claude-3-5-haiku-20241022"]}},"required":["provider","model"],"additionalProperties":false},{"type":"object","properties":{"provider":{"type":"string","const":"google"},"model":{"type":"string","enum":["gemini-1.5-pro","gemini-1.5-flash","gemini-2.0-flash","gemini-2.0-pro"]}},"required":["provider","model"],"additionalProperties":false},{"type":"object","properties":{"provider":{"type":"string"},"model":{"type":"string"}},"required":["provider","model"],"additionalProperties":false}]},{"type":"string"}],"default":{"provider":"openai","model":"gpt-4o"},"description":"LLM configuration"},"toolIds":{"type":"array","items":{"type":"string"},"description":"IDs of tools to use with this assistant"},"transcriber":{"type":"object","properties":{"provider":{"type":"string","description":"Provider to use for transcription"},"model":{"type":"string","description":"Transcription model to use"}},"required":["provider","model"],"additionalProperties":false,"default":{"provider":"deepgram","model":"nova-3"},"description":"Transcription configuration"},"voice":{"type":"object","properties":{"provider":{"type":"string","enum":["vapi","11labs","azure","cartesia","custom-voice","deepgram","11labs","hume","lmnt","neuphonic","openai","playht","rime-ai","smallest-ai","tavus","sesame"],"description":"Provider to use for voice"},"voiceId":{"type":"string","description":"Voice ID to use"},"model":{"type":"string","description":"Voice model to use"}},"required":["provider","voiceId"],"additionalProperties":false,"default":{"provider":"11labs","voiceId":"sarah"},"description":"Voice configuration"},"firstMessage":{"type":"string","default":"Hello, how can I help you today?","description":"First message to say to the user"},"firstMessageMode":{"type":"string","enum":["assistant-speaks-first","assistant-waits-for-user","assistant-speaks-first-with-model-generated-message"],"default":"assistant-speaks-first","description":"This determines who speaks first, either assistant or user"}},"required":["name"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}

Tool `update_assistant` has invalid JSON parameters:
	- Array has duplicate items. (at /properties/voice/properties/provider/enum)
	- Schema: {"type":"object","properties":{"assistantId":{"type":"string","description":"ID of the assistant to update"},"name":{"type":"string","description":"New name for the assistant"},"instructions":{"type":"string","description":"New instructions for the assistant"},"llm":{"anyOf":[{"anyOf":[{"type":"object","properties":{"provider":{"type":"string","const":"openai"},"model":{"type":"string","enum":["gpt-4o","gpt-4o-mini"]}},"required":["provider","model"],"additionalProperties":false},{"type":"object","properties":{"provider":{"type":"string","const":"anthropic"},"model":{"type":"string","enum":["claude-3-7-sonnet-20250219","claude-3-5-haiku-20241022"]}},"required":["provider","model"],"additionalProperties":false},{"type":"object","properties":{"provider":{"type":"string","const":"google"},"model":{"type":"string","enum":["gemini-1.5-pro","gemini-1.5-flash","gemini-2.0-flash","gemini-2.0-pro"]}},"required":["provider","model"],"additionalProperties":false},{"type":"object","properties":{"provider":{"type":"string"},"model":{"type":"string"}},"required":["provider","model"],"additionalProperties":false}]},{"type":"string"}],"description":"New LLM configuration"},"toolIds":{"type":"array","items":{"type":"string"},"description":"New IDs of tools to use with this assistant"},"transcriber":{"type":"object","properties":{"provider":{"type":"string","description":"Provider to use for transcription"},"model":{"type":"string","description":"Transcription model to use"}},"required":["provider","model"],"additionalProperties":false,"description":"New transcription configuration"},"voice":{"type":"object","properties":{"provider":{"type":"string","enum":["vapi","11labs","azure","cartesia","custom-voice","deepgram","11labs","hume","lmnt","neuphonic","openai","playht","rime-ai","smallest-ai","tavus","sesame"],"description":"Provider to use for voice"},"voiceId":{"type":"string","description":"Voice ID to use"},"model":{"type":"string","description":"Voice model to use"}},"required":["provider","voiceId"],"additionalProperties":false,"description":"New voice configuration"},"firstMessage":{"type":"string","description":"First message to say to the user"},"firstMessageMode":{"type":"string","enum":["assistant-speaks-first","assistant-waits-for-user","assistant-speaks-first-with-model-generated-message"],"description":"This determines who speaks first, either assistant or user"}},"required":["assistantId"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}

Thank you