# How to integrate Retellai MCP with Mastra AI

```json
{
  "title": "How to integrate Retellai MCP with Mastra AI",
  "toolkit": "Retellai",
  "toolkit_slug": "retellai",
  "framework": "Mastra AI",
  "framework_slug": "mastra-ai",
  "url": "https://composio.dev/toolkits/retellai/framework/mastra-ai",
  "markdown_url": "https://composio.dev/toolkits/retellai/framework/mastra-ai.md",
  "updated_at": "2026-05-12T10:24:04.939Z"
}
```

## Introduction

This guide walks you through connecting Retellai to Mastra AI using the Composio tool router. By the end, you'll have a working Retellai agent that can list all phone numbers linked to your account, retrieve call details for a specific agent this week, buy a new phone number with area code 415 through natural language commands.
This guide will help you understand how to give your Mastra AI agent real control over a Retellai account through Composio's Retellai MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Retellai with

- [OpenAI Agents SDK](https://composio.dev/toolkits/retellai/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/retellai/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/retellai/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/retellai/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/retellai/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/retellai/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/retellai/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/retellai/framework/cli)
- [Google ADK](https://composio.dev/toolkits/retellai/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/retellai/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/retellai/framework/ai-sdk)
- [LlamaIndex](https://composio.dev/toolkits/retellai/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/retellai/framework/crew-ai)

## TL;DR

Here's what you'll learn:
- Set up your environment so Mastra, OpenAI, and Composio work together
- Create a Tool Router session in Composio that exposes Retellai tools
- Connect Mastra's MCP client to the Composio generated MCP URL
- Fetch Retellai tool definitions and attach them as a toolset
- Build a Mastra agent that can reason, call tools, and return structured results
- Run an interactive CLI where you can chat with your Retellai agent

## What is Mastra AI?

Mastra AI is a TypeScript framework for building AI agents with tool support. It provides a clean API for creating agents that can use external services through MCP.
Key features include:
- MCP Client: Built-in support for Model Context Protocol servers
- Toolsets: Organize tools into logical groups
- Step Callbacks: Monitor and debug agent execution
- OpenAI Integration: Works with OpenAI models via @ai-sdk/openai

## What is the Retellai MCP server, and what's possible with it?

The Retellai MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Retellai account. It provides structured and secure access to your call records, phone numbers, and conversation transcripts, so your agent can perform actions like retrieving call details, managing phone numbers, initiating outbound calls, and analyzing voice data on your behalf.
- Retrieve and analyze call records: Your agent can fetch detailed call logs, filter by agent or time, and surface insights from past conversations.
- Initiate outbound and web-based calls: Easily direct your agent to start new phone or web calls between specific numbers or agents, supporting various business workflows.
- Manage phone numbers and assignments: Buy, update, or delete phone numbers, and bind them to agents for streamlined inbound and outbound call handling.
- Access and review call transcripts and details: Let your agent drill down into specific calls, pulling transcripts and metadata for compliance, training, or analytics.
- Explore and configure voice settings: Fetch detailed information about available voice options, including provider, accent, gender, and preview audio for customization of call experiences.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `RETELLAI_ADD_COMMUNITY_VOICE` | Add community voice | Add a community voice from ElevenLabs to your Retell voice library. Use when you need to import a shared community voice for use in your agents. |
| `RETELLAI_ADD_KNOWLEDGE_BASE_SOURCES` | Add sources to knowledge base | Tool to add sources (documents, URLs, text) to an existing knowledge base in Retell AI. Use when you need to add additional content to a knowledge base. At least one of knowledge_base_texts, knowledge_base_files, or knowledge_base_urls should be provided. |
| `RETELLAI_BUY_A_NEW_PHONE_NUMBER_BIND_AGENTS` | Buy a new phone number bind agents | This endpoint allows purchasing a new phone number with a specified area code and binding it to designated agents for inbound and outbound calls. It requires JSON with agent IDs and area code. Responses indicate the creation status or errors. A purchased phone number is a prerequisite for initiating outbound calls; an empty phone number inventory will prevent outbound calls from being made. |
| `RETELLAI_CREATE_AGENT` | Create Voice AI Agent | Create a new voice AI agent with specified configuration. Use when you need to set up a voice-based AI agent with custom response engine, voice settings, and behavior configuration. |
| `RETELLAI_CREATE_A_NEW_OUTBOUND_PHONE_CALL` | Create a new outbound phone call | Initiate an outbound call by POST to '/v2/create-phone-call'. Requires 'from_number' and 'to_number' in E.164 format. Optional overrides and metadata supported. On success, returns call details including type, status, and IDs. |
| `RETELLAI_CREATE_A_NEW_WEB_CALL` | Create a new web call | The /v2/create-web-call endpoint creates a web call with a unique agent ID, returning call details like type, token, call ID, and status in JSON format, with a 201 response. Optional metadata and variables can be included. |
| `RETELLAI_CREATE_BATCH_TEST` | Create Batch Test | Tool to create a batch test job that runs multiple test cases against an agent. Use when you need to evaluate agent performance across multiple test scenarios simultaneously. |
| `RETELLAI_CREATE_CHAT` | Create a new chat session | Tool to create a new chat session with a chat agent. Use when you need to initiate a new chat conversation with a RetellAI chat agent. |
| `RETELLAI_CREATE_CHAT_AGENT` | Create a new chat agent | Create a new chat agent with specified configuration. Use when you need to set up a chat-based AI agent with custom response engine and behavior settings. |
| `RETELLAI_CREATE_CHAT_COMPLETION` | Create chat completion | Tool to create a chat completion for an existing chat session, generating the agent's response to a user message. Use when you need the agent to respond to user input in an ongoing chat conversation. |
| `RETELLAI_CREATE_CONVERSATION_FLOW` | Create conversation flow | Create a new Conversation Flow that can be attached to an agent for response generation. Requires start_speaker, model_choice, and nodes. Returns conversation_flow_id and full configuration. |
| `RETELLAI_CREATE_CONVERSATION_FLOW_COMPONENT` | Create conversation flow component | Creates a new shared conversation flow component at POST '/create-conversation-flow-component'. Requires 'name' and 'nodes' array. Optional: tools, mcps, start_node_id, begin_tag_display_position. Returns component ID, timestamp, and the full component definition. |
| `RETELLAI_CREATE_KNOWLEDGE_BASE` | Create a new knowledge base | Tool to create a new knowledge base in Retell AI with texts, files, and URLs. Use when you need to create a knowledge base for an AI agent. At least one of knowledge_base_texts, knowledge_base_files, or knowledge_base_urls should be provided. |
| `RETELLAI_CREATE_RETELL_LLM` | Create Retell LLM Response Engine | Create a new Retell LLM Response Engine that can be attached to an agent. Use when you need to configure a new LLM-powered response system with custom prompts, tools, and conversation flows. |
| `RETELLAI_CREATE_TEST_CASE_DEFINITION` | Create Test Case Definition | Tool to create a test case definition for agent QA testing in Retell AI. Use when you need to define test scenarios for evaluating agent performance with specific user personas, goals, and success metrics. |
| `RETELLAI_DELETE_AGENT` | Delete agent | Deletes an existing agent by its unique identifier. Returns 204 No Content on successful deletion. |
| `RETELLAI_DELETE_CALL` | Delete call | Delete a specific call and its associated data by call ID. Use when you need to permanently remove a call record from the system. |
| `RETELLAI_DELETE_CHAT_AGENT` | Delete chat agent | Delete an existing chat agent by its unique identifier. Use when you need to permanently remove a chat agent from the system. |
| `RETELLAI_DELETE_CONVERSATION_FLOW` | Delete conversation flow | Delete a conversation flow and all its versions. Use when you need to permanently remove a conversation flow from the system. |
| `RETELLAI_DELETE_CONVERSATION_FLOW_COMPONENT` | Delete conversation flow component | Delete a shared conversation flow component. When deleting a shared component, creates local copies for all linked conversation flows. |
| `RETELLAI_DELETE_KNOWLEDGE_BASE` | Delete knowledge base | Delete an existing knowledge base by its unique identifier. Use when you need to permanently remove a knowledge base from the system. |
| `RETELLAI_DELETE_KNOWLEDGE_BASE_SOURCE` | Delete knowledge base source | Delete an existing source from a knowledge base. Use when you need to remove a specific document, text, or URL source from a knowledge base. |
| `RETELLAI_DELETE_PHONE_NUMBER` | Delete phone number | Tool to delete an existing phone number from Retell AI. Use when you need to remove a phone number that is no longer needed. The phone number must be in E.164 format (e.g., +14159998888). |
| `RETELLAI_DELETE_RETELL_LLM` | Delete Retell LLM | Delete an existing Retell LLM Response Engine by its unique identifier. Use when you need to permanently remove a Retell LLM from the system. |
| `RETELLAI_DELETE_TEST_CASE_DEFINITION` | Delete test case definition | Delete a test case definition by its unique identifier. Use when you need to permanently remove a test case definition from the system. |
| `RETELLAI_END_CHAT` | End chat | Tool to end an active chat session. Use when you need to terminate an ongoing chat conversation. |
| `RETELLAI_GET_AGENT` | Retrieve details of a specific agent | Retrieve details of a specific agent by its unique identifier. Use when you need to access agent configuration details. |
| `RETELLAI_GET_AGENT_VERSIONS` | Get agent versions | Tool to retrieve all versions of a specific agent. Use when you need to view version history or access previous configurations of an agent. |
| `RETELLAI_GET_BATCH_TEST` | Get batch test | Retrieve details and results of a specific batch test job. Use when you need to check the status and results of a batch test execution. |
| `RETELLAI_GET_CHAT` | Get chat details | Tool to retrieve details of a specific chat session by chat ID. Use when you need to access chat transcript, status, or analysis data. |
| `RETELLAI_GET_CHAT_AGENT` | Retrieve details of a specific chat agent | Retrieve details of a specific chat agent by its unique identifier. Use when you need to access chat agent configuration details. |
| `RETELLAI_GET_CHAT_AGENT_VERSIONS` | Get all versions of a chat agent | Retrieve all versions of a specific chat agent by its unique identifier. Use when you need to access version history of a chat agent. |
| `RETELLAI_GET_CONCURRENCY` | Get concurrency | Retrieves the current concurrency and concurrency limits for the organization. Use when you need to check concurrent call capacity and availability. |
| `RETELLAI_GET_CONVERSATION_FLOW` | Get Conversation Flow | Retrieve details of a specific Conversation Flow by its ID. Use when you need to fetch conversation flow configuration including nodes, version, and settings. |
| `RETELLAI_GET_CONVERSATION_FLOW_COMPONENT` | Get conversation flow component | Retrieves a shared conversation flow component by its unique identifier. Use when you need to fetch details of a specific conversation flow component. |
| `RETELLAI_GET_KNOWLEDGE_BASE` | Get knowledge base | Retrieve details of a specific knowledge base by its unique identifier. Use when you need to access knowledge base configuration including name, status, sources, and refresh settings. |
| `RETELLAI_GET_RETELL_LLM` | Retrieve details of a specific Retell LLM | Retrieve details of a specific Retell LLM Response Engine by its unique identifier. Use when you need to access LLM configuration including model settings, prompts, tools, states, and knowledge base configurations. |
| `RETELLAI_IMPORT_PHONE_NUMBER` | Import phone number | Tool to import a phone number from custom telephony and bind agents to it. Use when you need to integrate an existing phone number with Retell AI's system for handling inbound and outbound calls. |
| `RETELLAI_LIST_AGENTS` | List agents | Retrieves a list of all agents associated with the account. |
| `RETELLAI_LIST_ALL_CHATS` | List all chats | Tool to retrieve a list of all chats associated with the account. Use when you need to view chat history or analyze past conversations. |
| `RETELLAI_LIST_ALL_PHONE_NUMBERS` | List all phone numbers | Retrieves a list of all phone numbers associated with the account. An empty result means no phone numbers exist; RETELLAI_BUY_A_NEW_PHONE_NUMBER_BIND_AGENTS must be called before outbound calls can be made. |
| `RETELLAI_LIST_BATCH_TESTS` | List batch tests | Tool to list batch test jobs for a response engine. Use when you need to retrieve batch testing results for a Retell LLM or conversation flow. |
| `RETELLAI_LIST_CHAT_AGENTS` | List chat agents | Tool to retrieve a list of all chat agents associated with the account. Use when you need to view available chat agents or find specific chat agent configurations. |
| `RETELLAI_LIST_CONVERSATION_FLOW_COMPONENTS` | List conversation flow components | Retrieves a list of all shared conversation flow components. Use when you need to access reusable conversation flow building blocks that can be referenced across multiple conversation flows. |
| `RETELLAI_LIST_CONVERSATION_FLOWS` | List conversation flows | Tool to list all conversation flows that can be attached to an agent. Use when you need to retrieve available conversation flows for agent configuration. |
| `RETELLAI_LIST_KNOWLEDGE_BASES` | List knowledge bases | Tool to retrieve all knowledge bases associated with the account. Use when you need to list or view all available knowledge bases with their details including IDs, names, statuses, sources, and refresh settings. |
| `RETELLAI_LIST_RETELL_LLMS` | List Retell LLMs | Tool to list all Retell LLM Response Engines that can be attached to an agent. Use when you need to retrieve available LLM configurations including their IDs, models, prompts, tools, and other settings. |
| `RETELLAI_LIST_TEST_CASE_DEFINITIONS` | List test case definitions | Tool to list test case definitions for a response engine (Retell LLM or Conversation Flow). Use when you need to retrieve all test cases configured for a specific response engine and optionally a specific version. |
| `RETELLAI_LIST_TEST_RUNS` | List test runs | Tool to list all test case jobs (test runs) for a batch test job. Use when you need to retrieve execution results and details for all tests in a batch. |
| `RETELLAI_LIST_VOICES` | List voices | List all voices available to the user. Returns voice details including voice_id, name, provider, accent, gender, age, and preview audio URL. |
| `RETELLAI_PUBLISH_AGENT` | Publish agent | Publishes the latest version of the agent and creates a new draft agent with a newer version. Use when you need to deploy an agent to production. |
| `RETELLAI_PUBLISH_CHAT_AGENT` | Publish chat agent | Publishes the latest version of the chat agent and creates a new draft chat agent with a newer version. Use when you need to deploy a chat agent to production. |
| `RETELLAI_REGISTER_PHONE_CALL` | Register phone call | Register a phone call for custom telephony integration with Retell AI. Use when you need to register a call before connecting it to Retell's audio websocket for custom telephony providers. |
| `RETELLAI_RETRIEVE_CALL_DETAILS` | Retrieve call details | Tool to retrieve call details with filtering options. Use when you need to fetch call records, analyze call history, or monitor call performance. |
| `RETELLAI_RETRIEVE_CALL_DETAILS_BY_ID` | Retrieve call details by id | Retrieve call details by ID for web/phone calls, including type, agent ID, status, timestamps, and web access token; covering responses from success to server errors. |
| `RETELLAI_RETRIEVE_DETAILS_OF_A_SPECIFIC_PHONE_NUMBER` | Retrieve phone number details | Tool to retrieve details of a specific phone number from Retell AI. Use when you need to get information about a phone number including its type, timestamps, SIP configuration, and SMS settings. The phone number should be provided in E.164 format. |
| `RETELLAI_RETRIEVE_DETAILS_OF_A_SPECIFIC_VOICE` | Retrieve details of a specific voice | Tool to retrieve details of a specific voice by its voice_id. Use when you need information about a specific voice including its name, provider, accent, gender, age, and preview audio URL. |
| `RETELLAI_SEARCH_COMMUNITY_VOICE` | Search community voice | Search for community voices from voice providers. Use when you need to find voices by name, description, or ID, optionally filtering by provider. |
| `RETELLAI_UPDATE_AGENT` | Update agent | Update an existing agent's latest draft version. Use when modifying agent configuration, voice settings, or behavior parameters for a Retell AI agent. |
| `RETELLAI_UPDATE_CALL` | Update call | Update an active call's parameters such as metadata, dynamic variables, or data storage settings. Use when you need to modify call attributes during an ongoing call or update storage settings. |
| `RETELLAI_UPDATE_CHAT_AGENT` | Update chat agent | Update an existing chat agent configuration. Use when modifying chat agent settings, response engine, or behavior parameters. |
| `RETELLAI_UPDATE_CHAT_METADATA` | Update chat metadata | Tool to update metadata and sensitive data storage settings for an existing chat. Use when you need to modify chat metadata, custom attributes, or override dynamic variables. |
| `RETELLAI_UPDATE_CONVERSATION_FLOW` | Update conversation flow | Update an existing conversation flow configuration. Use when modifying conversation flow settings such as model parameters, nodes, tools, or prompt templates. |
| `RETELLAI_UPDATE_CONVERSATION_FLOW_COMPONENT` | Update conversation flow component | Update an existing shared conversation flow component by its ID. Use when you need to modify component properties like name, nodes, tools, or MCP configurations. |
| `RETELLAI_UPDATE_PHONE_NUMBER` | Update phone number configuration | Update agent bound to a purchased phone number. Use when you need to change the agent configuration, nickname, webhook URLs, or SIP settings for an existing phone number. |
| `RETELLAI_UPDATE_RETELL_LLM` | Update Retell LLM Response Engine | Update an existing Retell LLM Response Engine by its unique identifier. Use when you need to modify LLM configuration, prompts, tools, conversation flows, or model settings for an existing response engine. |
| `RETELLAI_UPDATE_TEST_CASE_DEFINITION` | Update test case definition | Update a test case definition for agent testing. Use when modifying test scenarios, metrics, or mock configurations for Retell AI agent validation. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Retellai MCP server is an implementation of the Model Context Protocol that connects your AI agent to Retellai. It provides structured and secure access so your agent can perform Retellai operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

Before starting, make sure you have:
- Node.js 18 or higher
- A Composio account with an active API key
- An OpenAI API key
- Basic familiarity with TypeScript

### 1. Getting API Keys for OpenAI and Composio

OpenAI API Key
- Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) and create an API key.
- You need credits or a connected billing setup to use the models.
- Store the key somewhere safe.
Composio API Key
- Log in to the [Composio dashboard](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs).
- Go to Settings and copy your API key.
- This key lets your Mastra agent talk to Composio and reach Retellai through MCP.

### 2. Install dependencies

Install the required packages.
What's happening:
- @composio/core is the Composio SDK for creating MCP sessions
- @mastra/core provides the Agent class
- @mastra/mcp is Mastra's MCP client
- @ai-sdk/openai is the model wrapper for OpenAI
- dotenv loads environment variables from .env
```bash
npm install @composio/core @mastra/core @mastra/mcp @ai-sdk/openai dotenv
```

### 3. Set up environment variables

Create a .env file in your project root.
What's happening:
- COMPOSIO_API_KEY authenticates your requests to Composio
- COMPOSIO_USER_ID tells Composio which user this session belongs to
- OPENAI_API_KEY lets the Mastra agent call OpenAI models
```bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here
```

### 4. Import libraries and validate environment

What's happening:
- dotenv/config auto loads your .env so process.env.* is available
- openai gives you a Mastra compatible model wrapper
- Agent is the Mastra agent that will call tools and produce answers
- MCPClient connects Mastra to your Composio MCP server
- Composio is used to create a Tool Router session
```typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Agent } from "@mastra/core/agent";
import { MCPClient } from "@mastra/mcp";
import { Composio } from "@composio/core";
import * as readline from "readline";

import type { AiMessageType } from "@mastra/core/agent";

const openaiAPIKey = process.env.OPENAI_API_KEY;
const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!openaiAPIKey) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey as string,
});
```

### 5. Create a Tool Router session for Retellai

What's happening:
- create spins up a short-lived MCP HTTP endpoint for this user
- The toolkits array contains "retellai" for Retellai access
- session.mcp.url is the MCP URL that Mastra's MCPClient will connect to
```typescript
async function main() {
  const session = await composio.create(
    composioUserID as string,
    {
      toolkits: ["retellai"],
    },
  );

  const composioMCPUrl = session.mcp.url;
  console.log("Retellai MCP URL:", composioMCPUrl);
```

### 6. Configure Mastra MCP client and fetch tools

What's happening:
- MCPClient takes an id for this client and a list of MCP servers
- The headers property includes the x-api-key for authentication
- getTools fetches the tool definitions exposed by the Retellai toolkit
```typescript
const mcpClient = new MCPClient({
    id: composioUserID as string,
    servers: {
      nasdaq: {
        url: new URL(composioMCPUrl),
        requestInit: {
          headers: session.mcp.headers,
        },
      },
    },
    timeout: 30_000,
  });

console.log("Fetching MCP tools from Composio...");
const composioTools = await mcpClient.getTools();
console.log("Number of tools:", Object.keys(composioTools).length);
```

### 7. Create the Mastra agent

What's happening:
- Agent is the core Mastra agent
- name is just an identifier for logging and debugging
- instructions guide the agent to use tools instead of only answering in natural language
- model uses openai("gpt-5") to configure the underlying LLM
```typescript
const agent = new Agent({
    name: "retellai-mastra-agent",
    instructions: "You are an AI agent with Retellai tools via Composio.",
    model: "openai/gpt-5",
  });
```

### 8. Set up interactive chat interface

What's happening:
- messages keeps the full conversation history in Mastra's expected format
- agent.generate runs the agent with conversation history and Retellai toolsets
- maxSteps limits how many tool calls the agent can take in a single run
- onStepFinish is a hook that prints intermediate steps for debugging
```typescript
let messages: AiMessageType[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end.\n");

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();

rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({
    id: crypto.randomUUID(),
    role: "user",
    content: trimmedInput,
  });

  console.log("\nAgent is thinking...\n");

  try {
    const response = await agent.generate(messages, {
      toolsets: {
        retellai: composioTools,
      },
      maxSteps: 8,
    });

    const { text } = response;

    if (text && text.trim().length > 0) {
      console.log(`Agent: ${text}\n`);
        messages.push({
          id: crypto.randomUUID(),
          role: "assistant",
          content: text,
        });
      }
    } catch (error) {
      console.error("\nError:", error);
    }

    rl.prompt();
  });

  rl.on("close", async () => {
    console.log("\nSession ended.");
    await mcpClient.disconnect();
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
```

## Complete Code

```typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Agent } from "@mastra/core/agent";
import { MCPClient } from "@mastra/mcp";
import { Composio } from "@composio/core";
import * as readline from "readline";

import type { AiMessageType } from "@mastra/core/agent";

const openaiAPIKey = process.env.OPENAI_API_KEY;
const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!openaiAPIKey) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({ apiKey: composioAPIKey as string });

async function main() {
  const session = await composio.create(composioUserID as string, {
    toolkits: ["retellai"],
  });

  const composioMCPUrl = session.mcp.url;

  const mcpClient = new MCPClient({
    id: composioUserID as string,
    servers: {
      retellai: {
        url: new URL(composioMCPUrl),
        requestInit: {
          headers: session.mcp.headers,
        },
      },
    },
    timeout: 30_000,
  });

  const composioTools = await mcpClient.getTools();

  const agent = new Agent({
    name: "retellai-mastra-agent",
    instructions: "You are an AI agent with Retellai tools via Composio.",
    model: "openai/gpt-5",
  });

  let messages: AiMessageType[] = [];

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (input: string) => {
    const trimmed = input.trim();
    if (["exit", "quit"].includes(trimmed.toLowerCase())) {
      rl.close();
      return;
    }

    messages.push({ id: crypto.randomUUID(), role: "user", content: trimmed });

    const { text } = await agent.generate(messages, {
      toolsets: { retellai: composioTools },
      maxSteps: 8,
    });

    if (text) {
      console.log(`Agent: ${text}\n`);
      messages.push({ id: crypto.randomUUID(), role: "assistant", content: text });
    }

    rl.prompt();
  });

  rl.on("close", async () => {
    await mcpClient.disconnect();
    process.exit(0);
  });
}

main();
```

## Conclusion

You've built a Mastra AI agent that can interact with Retellai through Composio's Tool Router.
You can extend this further by:
- Adding other toolkits like Gmail, Slack, or GitHub
- Building a web-based chat interface around this agent
- Using multiple MCP endpoints to enable cross-app workflows

## How to build Retellai MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/retellai/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/retellai/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/retellai/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/retellai/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/retellai/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/retellai/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/retellai/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/retellai/framework/cli)
- [Google ADK](https://composio.dev/toolkits/retellai/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/retellai/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/retellai/framework/ai-sdk)
- [LlamaIndex](https://composio.dev/toolkits/retellai/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/retellai/framework/crew-ai)

## Related Toolkits

- [Gmail](https://composio.dev/toolkits/gmail) - Gmail is Google's email service with powerful spam protection, search, and G Suite integration. It keeps your inbox organized and makes communication fast and reliable.
- [Outlook](https://composio.dev/toolkits/outlook) - Outlook is Microsoft's email and calendaring platform for unified communications and scheduling. It helps users stay organized with powerful email, contacts, and calendar management.
- [Slack](https://composio.dev/toolkits/slack) - Slack is a channel-based messaging platform for teams and organizations. It helps people collaborate in real time, share files, and connect all their tools in one place.
- [Gong](https://composio.dev/toolkits/gong) - Gong is a platform for video meetings, call recording, and team collaboration. It helps teams capture conversations, analyze calls, and turn insights into action.
- [Microsoft teams](https://composio.dev/toolkits/microsoft_teams) - Microsoft Teams is a collaboration platform that combines chat, meetings, and file sharing within Microsoft 365. It keeps distributed teams connected and productive through seamless virtual communication.
- [Slackbot](https://composio.dev/toolkits/slackbot) - Slackbot is a conversational automation tool for Slack that handles reminders, notifications, and automated responses. It boosts team productivity by streamlining onboarding, answering FAQs, and managing timely alerts—all right inside Slack.
- [2chat](https://composio.dev/toolkits/_2chat) - 2chat is an API platform for WhatsApp and multichannel text messaging. It streamlines chat automation, group management, and real-time messaging for developers.
- [Agent mail](https://composio.dev/toolkits/agent_mail) - Agent mail provides AI agents with dedicated email inboxes for sending, receiving, and managing emails. It empowers agents to communicate autonomously with people, services, and other agents—no human intervention needed.
- [Basecamp](https://composio.dev/toolkits/basecamp) - Basecamp is a project management and team collaboration tool by 37signals. It helps teams organize tasks, share files, and communicate efficiently in one place.
- [Chatwork](https://composio.dev/toolkits/chatwork) - Chatwork is a team communication platform with group chats, file sharing, and task management. It helps businesses boost collaboration and streamline productivity.
- [Clickmeeting](https://composio.dev/toolkits/clickmeeting) - ClickMeeting is a cloud-based platform for running online meetings and webinars. It helps businesses and individuals host, manage, and engage virtual audiences with ease.
- [Confluence](https://composio.dev/toolkits/confluence) - Confluence is Atlassian's team collaboration and knowledge management platform. It helps your team organize, share, and update documents and project content in one secure workspace.
- [Dailybot](https://composio.dev/toolkits/dailybot) - DailyBot streamlines team collaboration with chat-based standups, reminders, and polls. It keeps work flowing smoothly in your favorite messaging platforms.
- [Dialmycalls](https://composio.dev/toolkits/dialmycalls) - Dialmycalls is a mass notification service for sending voice and text messages to contacts. It helps teams and organizations quickly broadcast urgent alerts and updates.
- [Dialpad](https://composio.dev/toolkits/dialpad) - Dialpad is a cloud-based business phone and contact center system for teams. It unifies voice, video, messaging, and meetings across your devices.
- [Discord](https://composio.dev/toolkits/discord) - Discord is a real-time messaging and VoIP platform for communities and teams. It lets users chat, share media, and collaborate across public and private channels.
- [Discordbot](https://composio.dev/toolkits/discordbot) - Discordbot is an automation tool for Discord servers that handles moderation, messaging, and user engagement. It helps communities run smoothly by automating routine and complex tasks.
- [Echtpost](https://composio.dev/toolkits/echtpost) - Echtpost is a secure digital communication platform for encrypted document and message exchange. It ensures confidential data stays private and protected during transmission.
- [Egnyte](https://composio.dev/toolkits/egnyte) - Egnyte is a cloud-based platform for secure file sharing, storage, and governance. It helps teams collaborate efficiently while maintaining data compliance and security.
- [Google Meet](https://composio.dev/toolkits/googlemeet) - Google Meet is a secure video conferencing platform for virtual meetings, chat, and screen sharing. It helps teams connect, collaborate, and communicate seamlessly from anywhere.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Retellai MCP?

With a standalone Retellai MCP server, the agents and LLMs can only access a fixed set of Retellai tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Retellai and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with Mastra AI?

Yes, you can. Mastra AI fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Retellai tools.

### Can I manage the permissions and scopes for Retellai while using Tool Router?

Yes, absolutely. You can configure which Retellai scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Retellai data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)