retell_create_chat_agent

Create a text-based chat agent by configuring LLM engines and webhooks for conversational AI applications.

Instructions

Create a new chat agent for text-based conversations.

Input Schema

TableJSON Schema

Name	Required	Description
`response_engine`	Yes	The LLM engine configuration
`agent_name`	No	Display name for the chat agent
`webhook_url`	No	URL for receiving chat event webhooks

Implementation Reference

src/index.ts:1187-1188 (handler)
Handler logic for retell_create_chat_agent: makes a POST request to Retell API /create-chat-agent endpoint using the generic retellRequest helper.
```
case "retell_create_chat_agent":
  return retellRequest("/create-chat-agent", "POST", args);
```

src/index.ts:608-641 (schema)

Input schema defining parameters for creating a chat agent: response_engine (required with type and optional llm_id), agent_name, webhook_url.

{
  name: "retell_create_chat_agent",
  description: "Create a new chat agent for text-based conversations.",
  inputSchema: {
    type: "object",
    properties: {
      response_engine: {
        type: "object",
        description: "The LLM engine configuration",
        properties: {
          type: {
            type: "string",
            enum: ["retell-llm", "custom-llm"],
            description: "The type of response engine"
          },
          llm_id: {
            type: "string",
            description: "The LLM ID to use"
          }
        },
        required: ["type"]
      },
      agent_name: {
        type: "string",
        description: "Display name for the chat agent"
      },
      webhook_url: {
        type: "string",
        description: "URL for receiving chat event webhooks"
      }
    },
    required: ["response_engine"]
  }
},

src/index.ts:1283-1285 (registration)
Registers the listTools handler which returns the tools array containing retell_create_chat_agent.
```
server.setRequestHandler(ListToolsRequestSchema, async () => {
  return { tools };
});
```

src/index.ts:23-57 (helper)

Generic HTTP client for Retell API: handles authentication, request formatting, error handling, and JSON parsing. Used by all tool handlers.

async function retellRequest(
  endpoint: string,
  method: string = "GET",
  body?: Record<string, unknown>
): Promise<unknown> {
  const apiKey = getApiKey();

  const headers: Record<string, string> = {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  };

  const options: RequestInit = {
    method,
    headers,
  };

  if (body && method !== "GET") {
    options.body = JSON.stringify(body);
  }

  const response = await fetch(`${RETELL_API_BASE}${endpoint}`, options);

  if (!response.ok) {
    const errorText = await response.text();
    throw new Error(`Retell API error (${response.status}): ${errorText}`);
  }

  // Handle 204 No Content
  if (response.status === 204) {
    return { success: true };
  }

  return response.json();
}

src/index.ts:14-20 (helper)

Retrieves RETELL_API_KEY from environment and validates presence. Used by retellRequest.

function getApiKey(): string {
  const apiKey = process.env.RETELL_API_KEY;
  if (!apiKey) {
    throw new Error("RETELL_API_KEY environment variable is required");
  }
  return apiKey;
}

Retell AI MCP Server