How to integrate Elevenlabs MCP with Mastra AI

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Elevenlabs logo
Mastra AI logo
divider

Introduction

This guide walks you through connecting Elevenlabs to Mastra AI using the Composio tool router. By the end, you'll have a working Elevenlabs agent that can convert this chapter text to audio, create a custom project for your audiobook, add a new pronunciation rule for this word through natural language commands.

This guide will help you understand how to give your Mastra AI agent real control over a Elevenlabs account through Composio's Elevenlabs MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Elevenlabs with

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 Elevenlabs tools
  • Connect Mastra's MCP client to the Composio generated MCP URL
  • Fetch Elevenlabs 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 Elevenlabs 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 Elevenlabs MCP server, and what's possible with it?

The Elevenlabs MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Elevenlabs account. It provides structured and secure access to your voice synthesis projects and tools, so your agent can perform actions like generating audio from text, managing custom voices, organizing projects, and fine-tuning pronunciation on your behalf.

  • Project and chapter audio conversion: Instantly convert text content from chapters or entire projects into high-quality, natural-sounding audio files.
  • Custom voice creation and management: Guide your agent to add, finalize, or share custom voices—either by uploading new samples or assembling voices from existing data.
  • Pronunciation dictionary and rule management: Improve the accuracy of speech outputs by adding pronunciation dictionaries or custom pronunciation rules directly from files or specific aliases/phonemes.
  • Project organization and automation: Let your agent create new projects, add or remove chapters, and automate speech synthesis workflows for audiobooks, podcasts, or media production.
  • Embeddable audio player generation: Enable your agent to generate AudioNative projects, creating customizable and embeddable audio players from your content with just a prompt.

Supported Tools & Triggers

Tools
Add a pronunciation dictionary from fileAdds a new pronunciation dictionary from a lexicon file to improve speech synthesis accuracy.
Add outbound phone numberTool to import/register a Twilio phone number or SIP trunk into ElevenLabs Agents Platform.
Add new project with attributesUse to create a new ElevenLabs project for text-to-speech synthesis (e.
Add pronunciation dictionary from rulesTool to create a new pronunciation dictionary from provided rules for ElevenLabs text-to-speech.
Add rules to the pronunciation dictionaryAdds one or more custom pronunciation rules (alias or phoneme) to an existing pronunciation dictionary.
Add sharing voiceAdds an existing, shareable voice to a specified user's ElevenLabs account library under a new custom name, requiring the user's public ID and the voice ID.
Add a voiceAdds a custom voice by uploading audio samples for voice cloning.
Attach phone number to agentTool to assign or unassign an existing imported phone number to an agent by updating the phone number's assigned agent.
Calculate ConvAI Agent LLM UsageTool to calculate expected number of LLM tokens needed for a conversational AI agent.
Calculate ConvAI LLM UsageTool to calculate expected LLM usage costs for conversational AI agents.
Cancel Batch CallTool to cancel a running batch call and set all recipients to cancelled status.
Convert chapter to audioConverts the textual content of a chapter, identified by `chapter_id` within a `project_id`, into audio format.
Convert a projectConverts an existing ElevenLabs Studio project, including all its chapters and using its configured settings and voices, into speech.
Create a previously generated voiceFinalizes the creation of a voice using its `generated_voice_id` from a previous generation step by assigning a name, description, and optional labels.
Create Conversational AI Agent TestTool to create a new ElevenLabs Conversational AI agent response test.
Add to ConvAI Knowledge BaseTool to add documentation to ElevenLabs Conversational AI knowledge base by uploading a file or referencing a webpage URL.
Create ConvAI Knowledge Base FileTool to create a knowledge base document from an uploaded file for ElevenLabs Conversational AI agents.
Create ConvAI Knowledge Base FolderTool to create a folder in the ElevenLabs ConvAI knowledge base for organizing documents.
Create ConvAI Knowledge Base RAG IndexTool to compute or retrieve RAG indexes for multiple knowledge base documents in batch.
Create Knowledge Base Text DocumentTool to create a knowledge base document with text content in ElevenLabs Conversational AI.
Create Knowledge Base URL DocumentTool to create a knowledge base document by scraping the given webpage.
Create ConvAI Workspace SecretTool to create a new secret for the ElevenLabs ConvAI workspace.
Create Conversational AI ToolTool to create a new conversational AI tool in ElevenLabs workspace.
Create Conversational AI AgentTool to create a new ElevenLabs Conversational AI agent with specified configuration.
Generate Music Composition PlanTool to generate a music composition plan from a text prompt using ElevenLabs Music API.
Create an AudioNative enabled projectCreates an ElevenLabs AudioNative project, generating an embeddable audio player from a provided content file using text-to-speech, allowing customization of player appearance, audio settings, and conversion options.
Get similar library voicesReturns a list of shared voices similar to the provided audio sample.
Create Single Use TokenTool to generate a time-limited single-use token with embedded authentication for frontend clients.
Create Workspace WebhookTool to create a new webhook for the workspace with specified authentication type.
Delete chapter from projectIrreversibly deletes a specific, existing chapter from an existing project, typically to remove unwanted or obsolete content.
Delete Conversational AI AgentTool to permanently delete a Conversational AI agent by its unique identifier.
Delete agent response testTool to delete an agent response test by ID.
Delete batch callTool to permanently delete a batch call and all associated recipient records.
Delete conversation by IDTool to delete a particular Conversational AI conversation by ID.
Delete Knowledge Base Document or FolderTool to delete a document or folder from the knowledge base.
Delete ConvAI Knowledge Base RAG IndexTool to delete RAG index for a knowledge base document.
Delete workspace secretTool to delete a workspace secret if it's not in use.
Delete conversational AI toolTool to delete a conversational AI tool from the workspace by ID.
Delete a dubbing projectPermanently deletes a dubbing project by its ID; this action is irreversible and the project cannot be recovered.
Delete history itemPermanently deletes a specific history item (including its audio file and metadata) using its `history_item_id`; this operation is irreversible and should be used with caution.
Delete MCP serverTool to delete a specific MCP server configuration from the workspace.
Delete phone number by idTool to delete an imported phone number from the ElevenLabs workspace by ID.
Delete project by idUse to irreversibly delete a specific project by its `project_id`; the project must exist and be accessible, and this action cannot be undone.
Delete voice samplePermanently deletes a specific voice sample for a given voice ID; this action is irreversible.
Delete voice by idPermanently and irreversibly deletes a specific custom voice using its `voice_id`; the voice must exist and the authenticated user must have permission to delete it.
Delete workspace webhookTool to delete a specified workspace webhook by its ID.
Download history itemsDownloads audio clips from history by ID(s), returning a single file or a ZIP archive, with an optional output format (e.
Dub a video or an audio fileDub a video or audio file into a specified target language, requiring 'file' or 'source_url', 'target_lang', and 'csv_file' if 'mode' is 'manual'.
Duplicate Conversational AI AgentTool to create a new agent by duplicating an existing one.
Edit voiceUpdates the name, audio files, description, or labels for an existing voice model.
Edit voice settingsEdits key voice settings (e.
Generate a random voiceGenerates a unique, random ElevenLabs text-to-speech voice based on input text and specified voice characteristics.
Get agent detailsTool to retrieve available Conversational AI agents and outbound-capable Twilio phone numbers.
Get Agent LinkTool to get the current shareable link for a Conversational AI agent.
Get user profileRetrieves the profile information for the authenticated ElevenLabs user (identified by API key).
Get audio from history itemRetrieves the audio content for a specific history item from ElevenLabs, using a `history_item_id` that must correspond to a previously generated audio.
Get sample audioRetrieves the audio for a given `sample_id` that must belong to the specified `voice_id`.
Get audio native settingsTool to retrieve player settings for a specific Audio Native project.
Get chapter by IDFetches comprehensive details for a specific chapter within a given project, including its metadata (name, ID), conversion status, progress, download availability, and content statistics.
Get chapters by project idRetrieves a list of all chapters, their details, and conversion status for a project, useful for managing content or tracking progress.
Get chapter snapshotsRetrieves all saved version snapshots for a specific chapter within a given project, enabling review of its history or reversion to prior states.
Get Conversational AI AgentTool to retrieve the complete configuration for a specific Conversational AI agent by ID.
Get Agent Knowledge Base SizeTool to retrieve the number of pages in a conversational AI agent's knowledge base.
Get ConvAI Agents SummariesTool to retrieve summaries for specified Conversational AI agents.
Get Agent Widget ConfigTool to retrieve the widget configuration for a Conversational AI agent.
Get Agent Response Test By IDTool to retrieve an ElevenLabs Conversational AI agent response test by its ID.
Get conversational AI analytics live countTool to retrieve the live count of active ongoing Conversational AI conversations.
Get batch call detailsTool to get detailed information about a batch call including all recipients.
Get Batch Calls for WorkspaceTool to retrieve all batch calls for the current workspace.
Get Conversational AI ConversationsTool to retrieve all conversations of agents that user owns.
Get ConvAI Knowledge BaseTool to retrieve a list of available knowledge base documents.
Get Knowledge Base Document ContentTool to retrieve the entire content of a document from the knowledge base.
Get Knowledge Base Dependent AgentsTool to retrieve a list of agents depending on a specific knowledge base document.
Get Knowledge Base DocumentationTool to get details about a specific documentation making up the agent's knowledge base.
Get Knowledge Base RAG Index OverviewTool to retrieve RAG index overview including total size and usage information.
Get ConvAI Knowledge Base RAG IndexesTool to retrieve all RAG indexes for a specified knowledge base document.
Get Knowledge Base Source File URLTool to get a signed URL to download the original source file of a file-type document from the knowledge base.
Get Knowledge Base SummariesTool to retrieve knowledge base document summaries by their IDs.
Get ConvAI MCP ServerTool to retrieve a specific MCP server configuration from the workspace.
Get ConvAI MCP ServersTool to retrieve all MCP (Model Context Protocol) server configurations available in the workspace.
Get ConvAI MCP Server ToolsTool to retrieve all tools available for a specific MCP server configuration.
Get Phone Number by IDTool to retrieve detailed configuration for a specific phone number by ID.
Get ConvAI Workspace SecretsTool to retrieve all workspace secrets for the user.
Get Convai SettingsTool to retrieve Convai settings for the workspace.
Get Convai Dashboard SettingsTool to retrieve Convai dashboard settings for the workspace.
List Test InvocationsTool to list all test invocations for a specific conversational AI agent with pagination support.
Get Conversational AI ToolTool to retrieve the complete configuration for a specific conversational AI tool by ID.
Get ConvAI toolsTool to retrieve all available tools in the workspace.
Get Tool Dependent AgentsTool to retrieve a list of agents depending on a specific tool.
Get conversation by IDTool to fetch full details for a single Conversational AI conversation by ID.
Get Conversation Signed URLTool to get a signed URL to start a conversation with an agent that requires authorization.
Get default voice settingsRetrieves the ElevenLabs text-to-speech service's default voice settings (stability, similarity boost, style, speaker boost) that are applied when no voice-specific or request-specific settings are provided.
Get dubbed audio for a languageRetrieves an existing dubbed audio file for a specific `dubbing_id` and `language_code`.
Get dubbing project metadataRetrieves metadata and status for a specific dubbing project by its ID.
Get dubbing transcript in specific formatRetrieves the transcript for a specific dubbing project and language in the requested format (SRT, WebVTT, or JSON).
Get generated itemsRetrieves metadata for a list of generated audio items from history, supporting pagination and optional filtering by voice ID.
Get history item by idRetrieves detailed information (excluding the audio file) for a specific audio generation history item from ElevenLabs, using its unique ID.
Get MCP Tool ConfigurationTool to retrieve configuration overrides for a specific MCP tool within an MCP server.
Get pronunciation dictionary metadataRetrieves metadata for a specific, existing pronunciation dictionary from ElevenLabs using its ID.
Get modelsRetrieves a detailed list of all available ElevenLabs text-to-speech (TTS) models and their capabilities.
Get project by IDUse to retrieve all details for a specific project, including its chapters and their conversion statuses, by providing the project's unique ID.
Get projectsFetches a list of all projects and their details associated with the user's ElevenLabs account; this is a read-only operation.
Get project snapshotsRetrieves all available snapshots (saved states or versions) for an existing project, enabling history tracking, version comparison, or accessing specific states for playback/processing, particularly in text-to-speech workflows.
Get pronunciation dictionariesRetrieves a paginated list of pronunciation dictionaries, used to customize how specific words or phrases are pronounced by the text-to-speech (TTS) engine.
Get pronunciation dictionary versionDownloads the Pronunciation Lexicon Specification (PLS) file for an existing version of a pronunciation dictionary from ElevenLabs, used to customize TTS pronunciation.
Get Service AccountsTool to list all service accounts in the workspace.
Get shared voicesRetrieves a paginated and filterable list of shared voices from the ElevenLabs Voice Library.
Get sso provider adminRetrieves the SSO provider configuration for a specified workspace, typically for review purposes, and will indicate if no configuration exists.
Get Agent Response Test SummariesTool to retrieve multiple agent response test summaries by their IDs.
Get dubbing transcript by languageRetrieves the textual transcript for a specified dubbing project and language, if one exists for that language in the project.
Get Usage Character StatsTool to retrieve usage metrics for the current user or entire workspace.
Get user infoRetrieves detailed information about the authenticated ElevenLabs user's account, including subscription, usage, API key, and status.
Get user subscription infoRetrieves detailed subscription information for the currently authenticated ElevenLabs user.
Get voiceRetrieves comprehensive details for a specific, existing voice by its `voice_id`, optionally including its settings.
Get voices listRetrieves a list of all available voices along with their detailed attributes and settings.
Get voice settingsRetrieves the stability, similarity, style, and speaker boost settings for a specific, existing ElevenLabs voice using its `voice_id`.
Get workspace resource metadataTool to get metadata of a workspace resource by ID and type.
Get Workspace WebhooksTool to list all webhooks configured for the workspace.
List Conversational AI Agent TestsTool to list all agent response tests with pagination support and optional search filtering.
List DubsTool to list dubbing projects you have access to.
List Phone NumbersTool to list all imported phone numbers in the workspace.
List WhatsApp AccountsTool to list all WhatsApp accounts in the workspace.
Move Bulk Knowledge Base ItemsTool to move multiple documents or folders from one folder to another in the knowledge base.
Move ConvAI Knowledge Base EntityTool to move a knowledge base document or folder to a different folder.
Outbound callTool to place an outbound call via SIP trunk.
Get API documentationRetrieves the content of the official ElevenLabs API documentation page hosted on Mintlify.
Register Twilio Call for ConvAI AgentTool to register a Twilio call and return TwiML to connect the call to an ElevenLabs Conversational AI agent.
Remove rules from pronunciation dictionaryPermanently removes exact-match pronunciation rules from a specified ElevenLabs pronunciation dictionary using a list of rule strings; non-matching rule strings are ignored and this action cannot add or modify rules.
Resubmit Test InvocationsTool to resubmit specific test runs from a test invocation for a conversational AI agent.
Retry Batch CallTool to retry a batch call, calling failed and no-response recipients again.
Run Agent TestsTool to run selected tests on a conversational AI agent with optional configuration overrides.
Set Agent AvatarTool to set or update the avatar image for a Conversational AI agent displayed in the widget.
Simulate Conversational AI Agent ConversationTool to run a simulated conversation between an agent and an AI user.
Speech to speechConverts an input audio file to speech using a specified voice; if a `model_id` is provided, it must support speech-to-speech conversion.
Speech to speech streamingConverts an input audio stream to a different voice output stream in real-time, using a specified speech-to-speech model.
Stream audio isolationTool to remove background noise from audio and stream the isolated result.
Stream chapter audioStreams the audio for a specified chapter snapshot from an ElevenLabs project, optionally converting the output to MPEG format.
Stream ConvAI agent simulate conversationTool to run a simulated conversation between an agent and a simulated user, streaming back the response.
Stream project audioStreams audio from a specific project snapshot, optionally converting it to MPEG format.
Archive project snapshotArchives an existing project snapshot by its ID, creating a permanent, immutable, and typically irreversible copy of its state.
Submit Batch CallTool to submit a batch call.
Text to speechConverts text to speech using a specified ElevenLabs voice and model, returning a downloadable audio file (use ELEVENLABS_TEXT_TO_SPEECH_STREAM for streaming instead).
Text to speech streamConverts text to a spoken audio stream (no saved file or history entry); use the non-streaming text-to-speech tool when a persistent audio URL is needed.
Update Audio Native project contentTool to update content for an Audio Native project by uploading a text or HTML file.
Update Conversational AI AgentTool to update an existing ElevenLabs Conversational AI agent's settings.
Update Agent Response TestTool to update an existing ElevenLabs Conversational AI agent response test by ID.
Update Knowledge Base DocumentTool to update the name of a knowledge base document in ElevenLabs Conversational AI.
Update ConvAI Workspace SecretTool to update an existing secret in the ElevenLabs ConvAI workspace.
Update Convai SettingsTool to update Convai settings for the workspace.
Update Convai Dashboard SettingsTool to update Convai dashboard settings for the workspace.
Update Conversational AI ToolTool to update an existing conversational AI tool in ElevenLabs workspace.
Update project pronunciation dictionariesUpdates a project's pronunciation dictionaries on ElevenLabs to improve text-to-speech accuracy for specialized terms; note that while multiple dictionaries can be applied, the UI only displays the first.
Update pronunciation dictionaryPartially updates a pronunciation dictionary's metadata (name or archived status) without changing its version.
Update Workspace WebhookTool to update a specified workspace webhook by its ID.
Voice generation parameters retrievalFetches configurable parameters for ElevenLabs voice generation, used to determine available settings (e.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

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

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard 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.
  • Go to Settings and copy your API key.
  • This key lets your Mastra agent talk to Composio and reach Elevenlabs through MCP.

Install dependencies

bash
npm install @composio/core @mastra/core @mastra/mcp @ai-sdk/openai dotenv

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

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

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

Import libraries and validate environment

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,
});
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

Create a Tool Router session for Elevenlabs

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

  const composioMCPUrl = session.mcp.url;
  console.log("Elevenlabs MCP URL:", composioMCPUrl);
What's happening:
  • create spins up a short-lived MCP HTTP endpoint for this user
  • The toolkits array contains "elevenlabs" for Elevenlabs access
  • session.mcp.url is the MCP URL that Mastra's MCPClient will connect to

Configure Mastra MCP client and fetch tools

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);
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 Elevenlabs toolkit

Create the Mastra agent

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

Set up interactive chat interface

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: {
        elevenlabs: 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);
});
What's happening:
  • messages keeps the full conversation history in Mastra's expected format
  • agent.generate runs the agent with conversation history and Elevenlabs 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

Complete Code

Here's the complete code to get you started with Elevenlabs and Mastra AI:

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: ["elevenlabs"],
  });

  const composioMCPUrl = session.mcp.url;

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

  const composioTools = await mcpClient.getTools();

  const agent = new Agent({
    name: "elevenlabs-mastra-agent",
    instructions: "You are an AI agent with Elevenlabs 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: { elevenlabs: 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 Elevenlabs 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 Elevenlabs MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and Elevenlabs MCP?

With a standalone Elevenlabs MCP server, the agents and LLMs can only access a fixed set of Elevenlabs tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Elevenlabs 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 Elevenlabs tools.

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

Yes, absolutely. You can configure which Elevenlabs 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 Elevenlabs data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.