Skip to main content
Glama
ghl-mcp-server-v2

ghl-mcp-server-v2

by zackscriven

ghl_voice_ai_create_agent

Create a new voice AI agent configuration to define prompts, voice, language, working hours, and call handling for a GoHighLevel location.

Instructions

Create Agent Create a new voice AI agent configuration and settings Endpoint: POST /voice-ai/agents (Version header: v3; source: v3/voice-ai-v3.json) OAuth scopes: voice-ai-agents.write

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "body": "<body>"
    },
    "name": "ghl_voice_ai_create_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesRequest body (schema carried verbatim from the official OpenAPI spec).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv2.1.0
    • addedInput schema / properties / body / properties / agentWorkingHours / items / properties / intervals / items / title
      Added value: +"IntervalDTO"
    • addedInput schema / properties / body / properties / agentWorkingHours / items / title
      Added value: +"AgentWorkingHoursDTO"
    • addedInput schema / properties / body / properties / language / example
      Added value: +"en-US"
    • addedInput schema / properties / body / properties / language / title
      Added value: +"VoiceAILanguage"
    • addedInput schema / properties / body / properties / patienceLevel / example
      Added value: +"low"
    • addedInput schema / properties / body / properties / patienceLevel / title
      Added value: +"PatienceLevel"
    • changedInput schema / properties / body / properties / sendPostCallNotificationTo / allOf
      Previous value: -[
      -  {
      -    "properties": {
      -      "admins": {
      -        "description": "Enables post-call notifications to all admin users in the location. Default: true",
      -        "example": true,
      -        "type": "boolean"
      -      },
      -      "allUsers": {
      -        "description": "Enables post-call notifications to all users in the location. Default: false",
      -        "example": false,
      -        "type": "boolean"
      -      },
      -      "contactAssignedUser": {
      -        "description": "Enables post-call notifications to the user assigned to the contact. Default: false",
      -        "example": false,
      -        "type": "boolean"
      -      },
      -      "customEmails": {
      -        "description": "Array of custom email addresses to receive post-call notifications. Default: []",
      -        "example": [
      -          "manager@company.com"
      -        ],
      -        "items": {
      -          "type": "string"
      -        },
      -        "type": "array"
      -      },
      -      "specificUsers": {
      -        "description": "Array of specific user IDs to receive post-call notifications. Default: []",
      -        "example": [
      -          "user_507f1f77bcf86cd799439011"
      -        ],
      -        "items": {
      -          "type": "string"
      -        },
      -        "type": "array"
      -      }
      -    },
      -    "required": [
      -      "admins",
      -      "allUsers",
      -      "contactAssignedUser",
      -      "specificUsers",
      -      "customEmails"
      -    ],
      -    "type": "object"
      -  }
      -]New value: +[
      +  {
      +    "properties": {
      +      "admins": {
      +        "description": "Enables post-call notifications to all admin users in the location. Default: true",
      +        "example": true,
      +        "type": "boolean"
      +      },
      +      "allUsers": {
      +        "description": "Enables post-call notifications to all users in the location. Default: false",
      +        "example": false,
      +        "type": "boolean"
      +      },
      +      "contactAssignedUser": {
      +        "description": "Enables post-call notifications to the user assigned to the contact. Default: false",
      +        "example": false,
      +        "type": "boolean"
      +      },
      +      "customEmails": {
      +        "description": "Array of custom email addresses to receive post-call notifications. Default: []",
      +        "example": [
      +          "manager@company.com"
      +        ],
      +        "items": {
      +          "type": "string"
      +        },
      +        "type": "array"
      +      },
      +      "specificUsers": {
      +        "description": "Array of specific user IDs to receive post-call notifications. Default: []",
      +        "example": [
      +          "user_507f1f77bcf86cd799439011"
      +        ],
      +        "items": {
      +          "type": "string"
      +        },
      +        "type": "array"
      +      }
      +    },
      +    "required": [
      +      "admins",
      +      "allUsers",
      +      "contactAssignedUser",
      +      "specificUsers",
      +      "customEmails"
      +    ],
      +    "title": "SendPostCallNotificationDTO",
      +    "type": "object"
      +  }
      +]
    • changedInput schema / properties / body / properties / translation / allOf
      Previous value: -[
      -  {
      -    "properties": {
      -      "enabled": {
      -        "description": "Enables language translation for agent conversations. Default: false",
      -        "example": false,
      -        "type": "boolean"
      -      },
      -      "language": {
      -        "description": "Target language code for translation (e.g., \"es\" for Spanish, \"fr\" for French).",
      -        "example": "es",
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "enabled"
      -    ],
      -    "type": "object"
      -  }
      -]New value: +[
      +  {
      +    "properties": {
      +      "enabled": {
      +        "description": "Enables language translation for agent conversations. Default: false",
      +        "example": false,
      +        "type": "boolean"
      +      },
      +      "language": {
      +        "description": "Target language code for translation (e.g., \"es\" for Spanish, \"fr\" for French).",
      +        "example": "es",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "enabled"
      +    ],
      +    "title": "TranslationDTO",
      +    "type": "object"
      +  }
      +]
    • addedInput schema / properties / body / title
      Added value: +"AgentCreationRequestDTO"
  2. First observedv2.0.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=true, so the mutation and safety profile is covered structurally. The description adds genuine value by naming the OAuth scope (voice-ai-agents.write) and the API version header. It does not cover what happens on duplicate agent creation or whether unspecified fields fall back to defaults.

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

Conciseness4/5

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

It is short and front-loaded, with the action in the first line. The leading 'Create Agent' line merely repeats the annotation title and wastes a line. The endpoint and source metadata are terse but arguably noise for an agent that cannot call the endpoint directly.

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

Completeness5/5

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

Contextually this is close to complete: schema coverage is 100%, so parameters and defaults are self-documenting; annotations cover the mutation safety profile; and the description supplies the OAuth scope needed to know whether the call will succeed. The one real gap, sibling disambiguation, is scored under purpose clarity and usage guidelines rather than here.

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%, and the nested body schema already documents every field with defaults, ranges, enums, and translation rules. The description adds nothing about the body, so the baseline of 3 applies. The schema, not the description, does all the parameter work here.

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 names a specific verb and resource: create a new voice AI agent configuration and settings. That is clearer than a bare title restatement. However, it never distinguishes itself from the near-identical sibling ghl_conversation_ai_create_agent, nor from ghl_voice_ai_patch_agent, so the agent must infer which of the two 'create agent' tools applies.

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 gives no when-to-use guidance, no prerequisites, and no alternatives. The endpoint line and OAuth scope are implementation context, not selection guidance. The agent is left to guess between this and ghl_conversation_ai_create_agent.

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

Deploy Server

Other Tools