### Answer Yes, Retell has an MCP server that lets you build and manage voice agents from MCP-capable clients like Cursor, Claude Desktop, and Claude Code. [(1) ]() The MCP server gives your AI assistant native access to the Retell platform through a single integration. You can create, update, publish, list, and fetch agent versions, as well as manage calls, phone numbers, knowledge bases, voices, chats, testing, QA, alerts, and webhooks. To set it up, you'll need: - A Retell API key - An MCP client (Cursor, Claude Desktop, Claude Code, etc.) - Retell MCP server URL: ` For Claude Desktop specifically, you would add this to your config:

json
{
 "mcpServers": {
 "retell": {
 "url": "<https://retell.stlmcp.com%22,>
 "headers": {
 "Authorization": "Bearer <RETELL_API_KEY>"
 }
 }
 }
}

Once connected, you can use prompts like "Create a new agent for inbound sales qualification and publish it" or "List my agents and summarize what each one does."

​ To learn more, see the sources I considered: [[1] MCP Server](https://docs.retellai.com/get-started/mcp-server) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer The Retell MCP server capabilities for agents are available, and there is a Conversation Flow API that exists for programmatically defining conversational flows. [(1) ]() However, these flow definitions are managed via the Retell SDK or REST endpoints, not via Claude's MCP tool interface. The MCP server is great for invoking already configured agents, but it does not allow designing or updating conversation flow details from within the assistant UI. You can use the Conversation Flow API to create, update, and list conversation flows programmatically. [(2) ]() [(3) ]() For example, you can update a conversation flow using the SDK:

javascript
import Retell from 'retell-sdk';
const client = new Retell({
 apiKey: process.env['RETELL_API_KEY'],
}) ;
const conversationFlowResponse = await client.conversationFlow.update('conversation_flow_id') ;
console.log(conversationFlowResponse.conversation_flow_id) ;

[(3) ]() So while you can manage conversation flow agents programmatically through the API, the MCP server itself doesn't currently support building node-based conversation flows directly through Claude or other MCP clients.

​ To learn more, see the sources I considered: [[1] Retell MCP Server: Conversational Flow API](https://discord.com/channels/1186424376300679209/1400361046895493283) [[2] List Conversation Flows](https://docs.retellai.com/api-references/list-conversation-flows) [[3] Update Conversation Flow](https://docs.retellai.com/api-references/update-conversation-flow) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer I don't have specific information about "vibecode" agents in the available sources. However, I can help you understand the best ways to programmatically create and control Retell AI agents. For programmatic agent management, Retell provides official SDKs for Node.js and Python. [(1) ]() To get started: Install the SDK:

npm i retell-sdk

Initialize the client:

javascript
import Retell from 'retell-sdk';
const retellClient = new Retell({
 apiKey: "YOUR_API_KEY",
}) ;

For Conversation Flow agents specifically: You can retrieve conversation flow details programmatically: [(2) ]()

javascript
import Retell from 'retell-sdk';
const client = new Retell({
 apiKey: process.env['RETELL_API_KEY'], // This is the default and can be omitted
}) ;
const conversationFlowResponse = await client.conversationFlow.retrieve('conversation_flow_id') ;
console.log(conversationFlowResponse.conversation_flow_id) ;

The Conversation Flow API exists and allows you to programmatically define conversational flows using the Retell SDK or REST endpoints. [(3) ]() If "vibecode" refers to a specific framework or tool not covered in the Retell documentation, could you clarify what you mean? I can then provide more targeted guidance on integrating it with Retell AI's programmatic capabilities.

​ To learn more, see the sources I considered: [[1] SDKs](https://docs.retellai.com/get-started/sdk) [[2] Get Conversation Flow](https://docs.retellai.com/api-references/get-conversation-flow) [[3] Retell MCP Server: Conversational Flow API](https://discord.com/channels/1186424376300679209/1400361046895493283) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.