Skip to main content
Glama

vora_create_agent

Create a persistent voice agent tailored to your business use case. It learns from every call, compiles product knowledge, handles objections, selects optimal voice and language, and builds conversation workflows.

Instructions

Create a persistent voice agent for a specific use case. Uses your account context (from vora_register) plus any additional details you provide.

The voice agent persists across calls and improves with every conversation it has. Vora automatically:

  • Compiles product knowledge from your website and registration context

  • Generates objection handling based on your industry

  • Selects the optimal voice, language, and speaking style

  • Builds a conversation workflow (cold call, appointment, follow-up, etc.)

You can create multiple voice agents under one account for different use cases.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
account_idYesYour Vora account ID from vora_register.
objectiveYesWhat this voice agent does. Be specific. E.g., 'Cold call restaurant owners in Dubai to sell POS software at $99/mo' or 'Follow up with leads who downloaded our whitepaper about inventory management.'
workflowNoConversation workflow template. Auto-detected from objective if omitted.
languageNoPrimary language (ISO 639-1). Auto-detected from target market if omitted. E.g., 'ar' for Arabic, 'hi' for Hindi.
additional_contextNoExtra context beyond registration. Product updates, specific campaign details, competitor info, pricing changes.

Implementation Reference

  • The main handler function that registers the 'vora_create_agent' tool. Accepts account_id, objective, workflow, language, and additional_context. POSTs to /v1/agent-api/agents and returns the created agent details.
    export function registerVoraCreateAgent(server: McpServer): void {
      server.tool(
        "vora_create_agent",
        `Create a persistent voice agent for a specific use case. Uses your account context (from vora_register) plus any additional details you provide.
    
    The voice agent persists across calls and improves with every conversation it has. Vora automatically:
    - Compiles product knowledge from your website and registration context
    - Generates objection handling based on your industry
    - Selects the optimal voice, language, and speaking style
    - Builds a conversation workflow (cold call, appointment, follow-up, etc.)
    
    You can create multiple voice agents under one account for different use cases.`,
        {
          account_id: z
            .string()
            .describe("Your Vora account ID from vora_register."),
          objective: z
            .string()
            .describe(
              "What this voice agent does. Be specific. E.g., 'Cold call restaurant owners in Dubai to sell POS software at $99/mo' or 'Follow up with leads who downloaded our whitepaper about inventory management.'"
            ),
          workflow: z
            .enum(["cold_call", "appointment_set", "follow_up", "callback", "custom"])
            .optional()
            .describe(
              "Conversation workflow template. Auto-detected from objective if omitted."
            ),
          language: z
            .string()
            .optional()
            .describe(
              "Primary language (ISO 639-1). Auto-detected from target market if omitted. E.g., 'ar' for Arabic, 'hi' for Hindi."
            ),
          additional_context: z
            .string()
            .optional()
            .describe(
              "Extra context beyond registration. Product updates, specific campaign details, competitor info, pricing changes."
            ),
        },
        async (params) => {
          const client = getApiClient();
    
          try {
            const response = await client.post<CreateAgentResponse>(
              "/v1/agent-api/agents",
              {
                account_id: params.account_id,
                objective: params.objective,
                workflow: params.workflow,
                language: params.language,
                additional_context: params.additional_context,
              }
            );
    
            return {
              content: [
                {
                  type: "text" as const,
                  text: `Voice agent created!\n\nAgent ID: ${response.agent_id}\nName: ${response.name}\nObjective: ${response.objective}\nWorkflow: ${response.workflow}\nLanguage: ${response.language}\nEst. cost per call: ${response.estimated_cost_per_call}\nVoice preview: ${response.voice_preview_url}\nContext sources: ${response.context_sources.join(", ")}\n\nReady to make calls. Use vora_call with this agent_id.`,
                },
              ],
            };
          } catch (error) {
            return {
              content: [
                {
                  type: "text" as const,
                  text: `Agent creation error: ${error instanceof Error ? error.message : String(error)}`,
                },
              ],
              isError: true,
            };
          }
        }
      );
    }
  • Response interface for the agent creation API call, containing agent_id, name, objective, workflow, language, voice preview URL, estimated cost, and context sources.
    interface CreateAgentResponse {
      agent_id: string;
      name: string;
      objective: string;
      workflow: string;
      language: string;
      voice_preview_url: string;
      estimated_cost_per_call: string;
      context_sources: string[];
    }
  • The tool is registered in the central tools index. registerVoraCreateAgent is imported and called with the McpServer instance.
    import { registerVoraCreateAgent } from "./vora-create-agent.js";
    import { registerVoraCall } from "./vora-call.js";
    import { registerVoraCalls } from "./vora-calls.js";
    import { registerVoraUpdateAgent } from "./vora-update-agent.js";
    
    export function registerTools(server: McpServer): void {
      registerVoraRegister(server);
      registerVoraCreateAgent(server);
      registerVoraCall(server);
      registerVoraCalls(server);
      registerVoraUpdateAgent(server);
  • The getApiClient helper used by the handler to obtain the API client for making HTTP requests to the Vora backend.
    let client: VoraApiClient | null = null;
    export function getApiClient(): VoraApiClient {
      if (!client) client = new VoraApiClient();
      return client;
    }
Behavior5/5

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

Without annotations, the description carries full burden. It discloses key behaviors: the agent persists across calls, improves over time, and automatically compiles knowledge, generates objection handling, selects voice/language, and builds workflows. This provides sufficient transparency.

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 concise and well-structured. It starts with a clear purpose, then uses bullet points to list automatic features. Every sentence is informative without redundancy.

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

Completeness4/5

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

Given 5 parameters and no output schema, the description covers prerequisites, automatic behaviors, and parameter details. It does not specify the return value (e.g., agent ID), but this is a minor gap. Overall, it provides sufficient context for using the tool.

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

Parameters4/5

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

Schema description coverage is 100%, so baseline is 3. The description adds value by noting auto-detection for 'workflow' and 'language', and clarifying 'additional_context' as extra beyond registration. This enhances understanding beyond the schema.

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

Purpose5/5

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

The description clearly states the tool's purpose: 'Create a persistent voice agent for a specific use case.' It uses a specific verb ('create') and resource ('voice agent'), and distinguishes from sibling tools like vora_update_agent by focusing on creation.

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

Usage Guidelines4/5

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

The description explains the prerequisite of having a registered account (via vora_register) and notes that multiple agents can be created for different use cases. It implies when to use the tool, but does not explicitly contrast with alternatives like vora_update_agent.

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/stefanstojanovicstefa-creator/vora-voice-mcp'

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