How to integrate Scale ai MCP with Mastra AI

GET STARTED FOR FREE
Framework Integration Gradient
Scale ai Logo
Mastra AI Logo
divider

Introduction

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.

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.

Supported Tools & Triggers

Tools
Add Studio AssignmentsTool to add project assignments to team members in Scale AI Studio.
Add Task TagsTool to add tags to an existing task.
Create BatchTool to create a new batch within a project.
Create Document Transcription TaskTool to create a document transcription task where workers transcribe and annotate information from single or multi-page documents.
Create Image Annotation TaskTool to create an image annotation task where annotators label images with vector geometric shapes (box, polygon, line, point, cuboid, ellipse).
Create Lidar Annotation TaskTool to create a lidar annotation task where annotators mark objects with 3D cuboids in 3D space.
Create LiDAR Segmentation TaskTool to create a LiDAR segmentation task where annotators assign semantic class labels to individual LiDAR points.
Create Named Entity Recognition TaskTool to create a named entity recognition task for labelers to highlight text entity mentions.
Create Segmentation Annotation TaskTool to create a segmentation task where annotators classify pixels in an image according to provided labels.
Create Text Collection TaskTool to create a textcollection task for collecting information from attachments and/or web sources.
Create Video Annotation TaskTool to create a video annotation task where annotators draw geometric shapes around specified objects across video frames.
Create Video Playback Annotation TaskTool to create a video playback annotation task where annotators draw shapes around specified objects in video files.
Delete Task TagsTool to remove specified tags from a Scale AI task.
Delete Task Unique IDTool to remove the unique identifier from a task.
Finalize BatchTool to finalize a batch so its tasks can be worked on.
Get AssetsTool to retrieve file assets with filtering capabilities by project and metadata.
Get BatchTool to retrieve the details of a batch with the specified name.
Get Batch StatusTool to retrieve the current status of a batch and task completion counts.
Get Fixless AuditsTool to retrieve fixless audits by task ID or audit ID.
Get ProjectTool to retrieve details about a specific Scale AI project using its unique identifier.
Get Quality LabelersTool to retrieve training attempts matching provided filter parameters.
Get Studio AssignmentsTool to retrieve current project assignments of all active team users in Scale AI Studio.
Get Studio BatchesTool to retrieve basic information about all pending batches in Studio.
Get TaskTool to retrieve detailed information about a specific task in Scale AI.
Get TeamsTool to retrieve basic information about all team members associated with the account.
Get Task by IDTool to retrieve detailed information about a specific task using its task ID.
Get Secure Task Response URLTool to retrieve secure authenticated task response data.
Import FileTool to import files from an external URL endpoint into Scale's system rather than uploading directly from local storage.
Invite Team MemberTool to invite users by email to team with specified role.
List BatchesTool to retrieve all batches in descending order by creation date.
List ProjectsTool to retrieve information for all projects in the Scale AI account with optional archived filtering.
List TasksTool to retrieve a paginated list of tasks in descending order by creation time.
Re-send Task CallbackTool to re-send a callback for a completed or errored task to the callback_url.
Remove Studio AssignmentsTool to unassign projects from specified team members in Scale AI Studio.
Reset Batch PrioritiesTool to restore batch priority order to default order (calibration batches first, then sorted by creation date).
Set Batch PrioritiesTool to modify batch priority order in Scale AI Studio.
Set Project OntologyTool to set ontologies on a Scale AI project.
Set Project ParametersTool to set default parameters for tasks created under a project.
Set Task MetadataTool to set key-value metadata on an existing Scale AI task.
Update Task Unique IDTool to update or assign a unique identifier to a task.
Upload FileTool to upload a local file to Scale's servers with a maximum size limit of 80 MB per file.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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 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

How to build Scale ai MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Scale ai MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Scale ai MCP with Claude Agent SDK

Google ADK

Google ADK

Use Scale ai MCP with Google ADK

LangChain

LangChain

Use Scale ai MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Scale ai MCP with Vercel AI SDK

LlamaIndex

LlamaIndex

Use Scale ai MCP with LlamaIndex

CrewAI

CrewAI

Use Scale ai MCP with CrewAI

Claude Code

Claude Code

Use Scale ai MCP with Claude Code

Codex

Codex

Use Scale ai MCP with Codex

FAQ

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

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.

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 Scale ai tools.

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

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.

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 Scale ai 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.

Book a call↗Get started for free