How to integrate Scale ai MCP with Mastra AI

This guide walks you through connecting Scale ai to Mastra AI using the Composio tool router. By the end, you'll have a working Scale ai agent that can create image labeling task for dataset 'road-signs', list completed annotation tasks for project, fetch results of data labeling job through natural language commands. This guide will help you understand how to give your Mastra AI agent real control over a Scale ai account through Composio's Scale ai MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for free Get a demo

Scale ai

Api Key

Scale ai provides machine learning data labeling and annotation services. It enables teams to train AI models with high-quality, human-labeled data at scale.

41 Tools

Managed auth

Connect Scale ai without auth hassles

We manage OAuth, API keys, token refresh, and scopes — you just build.

Try for free

Introduction

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

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

Also integrate Scale ai with

OpenAI Agents SDK Claude Agent SDK Claude Code Claude Cowork Codex OpenClaw Hermes CLI Google ADK LangChain Vercel AI SDK LlamaIndex CrewAI

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

The Scale ai MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Scale ai account. It provides structured and secure access so your agent can perform Scale ai operations on your behalf.

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:

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

Step-by-step Guide

Step by step09 STEPS

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 Scale ai 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 Scale ai

typescript

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

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

What's happening:

create spins up a short-lived MCP HTTP endpoint for this user
The toolkits array contains "scale_ai" for Scale ai 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 Scale ai toolkit

Create the Mastra agent

typescript

const agent = new Agent({
    name: "scale_ai-mastra-agent",
    instructions: "You are an AI agent with Scale ai 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: {
        scale_ai: 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 Scale ai 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 Scale ai 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: ["scale_ai"],
  });

  const composioMCPUrl = session.mcp.url;

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

  const composioTools = await mcpClient.getTools();

  const agent = new Agent({
    name: "scale_ai-mastra-agent",
    instructions: "You are an AI agent with Scale ai 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: { scale_ai: 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 Scale ai 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

TOOLS

Supported Tools

Every Scale ai action and event your agent gets out of the box.

Add Studio Assignments

Tool to add project assignments to team members in Scale AI Studio.

Add Task Tags

Tool to add tags to an existing task.

Create Batch

Tool to create a new batch within a project.

Create Document Transcription Task

Tool to create a document transcription task where workers transcribe and annotate information from single or multi-page documents.

Create Image Annotation Task

Tool to create an image annotation task where annotators label images with vector geometric shapes (box, polygon, line, point, cuboid, ellipse).

Create Lidar Annotation Task

Tool to create a lidar annotation task where annotators mark objects with 3D cuboids in 3D space.

Create LiDAR Segmentation Task

Tool to create a LiDAR segmentation task where annotators assign semantic class labels to individual LiDAR points.

Create Named Entity Recognition Task

Tool to create a named entity recognition task for labelers to highlight text entity mentions.

Create Segmentation Annotation Task

Tool to create a segmentation task where annotators classify pixels in an image according to provided labels.

Create Text Collection Task

Tool to create a textcollection task for collecting information from attachments and/or web sources.

Create Video Annotation Task

Tool to create a video annotation task where annotators draw geometric shapes around specified objects across video frames.

Create Video Playback Annotation Task

Tool to create a video playback annotation task where annotators draw shapes around specified objects in video files.

Delete Task Tags

Tool to remove specified tags from a Scale AI task.

Delete Task Unique ID

Tool to remove the unique identifier from a task.

Finalize Batch

Tool to finalize a batch so its tasks can be worked on.

Get Assets

Tool to retrieve file assets with filtering capabilities by project and metadata.

Get Batch

Tool to retrieve the details of a batch with the specified name.

Get Batch Status

Tool to retrieve the current status of a batch and task completion counts.

Get Fixless Audits

Tool to retrieve fixless audits by task ID or audit ID.

Get Project

Tool to retrieve details about a specific Scale AI project using its unique identifier.

Get Quality Labelers

Tool to retrieve training attempts matching provided filter parameters.

Get Studio Assignments

Tool to retrieve current project assignments of all active team users in Scale AI Studio.

Get Studio Batches

Tool to retrieve basic information about all pending batches in Studio.

Get Task

Tool to retrieve detailed information about a specific task in Scale AI.

Get Teams

Tool to retrieve basic information about all team members associated with the account.

Get Task by ID

Tool to retrieve detailed information about a specific task using its task ID.

Get Secure Task Response URL

Tool to retrieve secure authenticated task response data.

Import File

Tool to import files from an external URL endpoint into Scale's system rather than uploading directly from local storage.

Invite Team Member

Tool to invite users by email to team with specified role.

List Batches

Tool to retrieve all batches in descending order by creation date.

List Projects

Tool to retrieve information for all projects in the Scale AI account with optional archived filtering.

List Tasks

Tool to retrieve a paginated list of tasks in descending order by creation time.

Re-send Task Callback

Tool to re-send a callback for a completed or errored task to the callback_url.

Remove Studio Assignments

Tool to unassign projects from specified team members in Scale AI Studio.

Reset Batch Priorities

Tool to restore batch priority order to default order (calibration batches first, then sorted by creation date).

Set Batch Priorities

Tool to modify batch priority order in Scale AI Studio.

Set Project Ontology

Tool to set ontologies on a Scale AI project.

Set Project Parameters

Tool to set default parameters for tasks created under a project.

Set Task Metadata

Tool to set key-value metadata on an existing Scale AI task.

Update Task Unique ID

Tool to update or assign a unique identifier to a task.

Upload File

Tool to upload a local file to Scale's servers with a maximum size limit of 80 MB per file.

FRAMEWORKS

How to build Scale ai MCP Agent with another framework

OpenAI Agents SDK

Use Scale ai MCP with OpenAI Agents SDK

Claude Agent SDK

Use Scale ai MCP with Claude Agent SDK

Claude Code

Use Scale ai MCP with Claude Code

Claude Cowork

Use Scale ai MCP with Claude Cowork

Codex

Use Scale ai MCP with Codex

OpenClaw

Use Scale ai MCP with OpenClaw

Hermes

Use Scale ai MCP with Hermes

CLI

Use Scale ai MCP with CLI

Google ADK

Use Scale ai MCP with Google ADK

LangChain

Use Scale ai MCP with LangChain

Vercel AI SDK

Use Scale ai MCP with Vercel AI SDK

LlamaIndex

Use Scale ai MCP with LlamaIndex

CrewAI

Use Scale ai MCP with CrewAI

MORE TOOLKITS

Explore Other Toolkits

Toolkit marketplace

Google Sheets

Oauth2

Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly.

Composio

No Auth

Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed.

Notion

Oauth2Api Key

Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place.

Airtable

Oauth2Api Key

Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations.

FAQ

Frequently asked questions

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

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 Scale ai tools.

Yes, absolutely. You can configure which Scale ai 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.

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 Scale ai data and credentials are handled as safely as possible.

Start with Scale ai.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Scale ai tool your agent needs.Free to start.

Start building

Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREE BOOK A DEMO

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati

Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya

Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave

CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu

Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola

Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche

Co-Founder, Ingram Technologies

How to integrate Scale ai MCP with Mastra AI

Connect Scale ai without auth hassles

Introduction

Also integrate Scale ai with

TL;DR

What is Mastra AI?

What is the Scale ai MCP server, and what's possible with it?

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

What is Composio SDK?

How the Composio SDK works

Step-by-step Guide

Prerequisites

Getting API Keys for OpenAI and Composio

Install dependencies

Set up environment variables

Import libraries and validate environment

Create a Tool Router session for Scale ai

Configure Mastra MCP client and fetch tools

Create the Mastra agent

Set up interactive chat interface

Complete Code

Conclusion

Supported Tools

How to build Scale ai MCP Agent with another framework

OpenAI Agents SDK

Claude Agent SDK

Claude Code

Claude Cowork

Codex

OpenClaw

Hermes

CLI

Google ADK

LangChain

Vercel AI SDK

LlamaIndex

CrewAI

Explore Other Toolkits

Google Sheets

Composio

Notion

Airtable

Frequently asked questions

What are the differences in Tool Router MCP and Scale ai MCP?+

Can I use Tool Router MCP with Mastra AI?+

Can I manage the permissions and scopes for Scale ai while using Tool Router?+

How safe is my data with Composio Tool Router?+

Start with Scale ai.It takes 30 seconds.

Teams ship real agents on Composio