Skip to main content
Glama
AiAgency-Now

VoiceAI-MCP-VAVicky

Official
by AiAgency-Now

create_assistant

Configure and deploy AI assistants for voice or text interactions by setting parameters like provider, model, voice, and integration options.

Instructions

Create a new assistant with comprehensive configuration

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesAssistant name
apiKeyYesOpenAI API Key
welcome_messageNoWelcome messageHello how can I help you today?
promptNoInstructions/Prompt for the assistant
activeNoWhether assistant is active
assistant_typeNoAI Type
ai_platformNoAI Provider
openai_modelNoAI Modelgpt-3.5-turbo
openai_temperatureNoAI Temperature (0-2)
booking_botNoIs booking bot
locationNoGoHighLevel Location
calendarNoCalendar ID
timezoneNoTimezone
custom_fieldNoCustom field
limit_call_timeNoLimit call time in seconds
limit_call_tokensNoLimit call tokens
max_call_tokensNoMax call tokens
elevenlabs_voice_idNoElevenLabs Voice ID
twilio_sidNoTwilio SID
twilio_tokenNoTwilio Token
twilio_phoneNoTwilio Phone Number
twilio_welcomeNoTwilio Welcome Message
twilio_speech_timeoutNoTwilio Speech Timeout
twilio_initial_delayNoTwilio Initial Delay
google_calendarNoGoogle Calendar Integration
webhook_to_sendNoWebhook URL
openai_realtimeNoOpenAI Realtime
openai_realtime_voiceNoOpenAI Realtime Voice
openai_websitesNoOpenAI Websites

Implementation Reference

  • Switch case handling the 'create_assistant' tool: constructs a POST request to `${baseUrl}/assistants` with body from filtered arguments.
    case 'create_assistant':
      url = `${this.baseUrl}/assistants`;
      method = 'POST';
      body = this.filterEmptyValues(args);
      break;
  • Tool definition including name, description, and detailed inputSchema for 'create_assistant' parameters.
    {
      name: 'create_assistant',
      description: 'Create a new assistant with comprehensive configuration',
      inputSchema: {
        type: 'object',
        properties: {
          name: { type: 'string', description: 'Assistant name' },
          apiKey: { type: 'string', description: 'OpenAI API Key' },
          welcome_message: { type: 'string', description: 'Welcome message', default: 'Hello how can I help you today?' },
          prompt: { type: 'string', description: 'Instructions/Prompt for the assistant' },
          active: { type: 'boolean', description: 'Whether assistant is active', default: true },
          assistant_type: { type: 'string', enum: ['Text Only', 'Voice Only', 'Text & Voice', 'Voice & Text'], description: 'AI Type' },
          ai_platform: { type: 'string', enum: ['openai', 'gemini', 'openrouter', 'deepseek'], description: 'AI Provider' },
          openai_model: { type: 'string', description: 'AI Model', default: 'gpt-3.5-turbo' },
          openai_temperature: { type: 'number', description: 'AI Temperature (0-2)', default: 0.8 },
          booking_bot: { type: 'boolean', description: 'Is booking bot', default: false },
          location: { type: 'string', description: 'GoHighLevel Location' },
          calendar: { type: 'string', description: 'Calendar ID' },
          timezone: { type: 'string', description: 'Timezone' },
          custom_field: { type: 'string', description: 'Custom field' },
          limit_call_time: { type: 'number', description: 'Limit call time in seconds', default: 240 },
          limit_call_tokens: { type: 'number', description: 'Limit call tokens', default: 2000 },
          max_call_tokens: { type: 'number', description: 'Max call tokens', default: 18000 },
          elevenlabs_voice_id: { type: 'string', description: 'ElevenLabs Voice ID' },
          twilio_sid: { type: 'string', description: 'Twilio SID' },
          twilio_token: { type: 'string', description: 'Twilio Token' },
          twilio_phone: { type: 'string', description: 'Twilio Phone Number' },
          twilio_welcome: { type: 'string', description: 'Twilio Welcome Message' },
          twilio_speech_timeout: { type: 'number', description: 'Twilio Speech Timeout', default: 3 },
          twilio_initial_delay: { type: 'number', description: 'Twilio Initial Delay', default: 1 },
          google_calendar: { type: 'boolean', description: 'Google Calendar Integration', default: false },
          webhook_to_send: { type: 'string', description: 'Webhook URL' },
          openai_realtime: { type: 'boolean', description: 'OpenAI Realtime', default: false },
          openai_realtime_voice: { type: 'string', enum: ['alloy', 'echo', 'fable', 'nova', 'onyx', 'shimmer'], description: 'OpenAI Realtime Voice' },
          openai_websites: { type: 'array', items: { type: 'string' }, description: 'OpenAI Websites' }
        },
        required: ['name', 'apiKey']
      }
    },
  • Utility function used by create_assistant (and others) to filter out empty/undefined values from the request body.
    filterEmptyValues(obj) {
      const cleaned = {};
      for (const [key, value] of Object.entries(obj)) {
        if (value !== undefined && value !== null && value !== '') {
          cleaned[key] = value;
        }
      }
      return cleaned;
    }
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. 'Create' implies a write/mutation operation, but the description doesn't mention authentication requirements, rate limits, side effects, or what happens on success/failure. For a complex creation tool with 29 parameters, this is a significant gap in behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that communicates the core purpose without unnecessary elaboration. Every word earns its place, making it appropriately sized for the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex creation tool with 29 parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain what an 'assistant' is in this context, what happens after creation, or how this tool relates to the sibling tools. The agent would need to infer too much from the parameter names alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 29 parameters thoroughly. The description adds minimal value beyond stating 'comprehensive configuration', which is already evident from the extensive parameter list. This meets the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Create') and resource ('a new assistant'), and specifies the scope ('with comprehensive configuration'). It doesn't explicitly differentiate from sibling tools like 'update_assistant', but the creation purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'update_assistant' or 'get_assistant'. There's no mention of prerequisites, dependencies, or contextual constraints that would help an agent decide when this is the appropriate tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/AiAgency-Now/MCP-VoiceAI-WhiteLabel'

If you have feedback or need assistance with the MCP directory API, please join our Discord server