How to integrate Scale ai MCP with LangChain

GET STARTED FOR FREE
Framework Integration Gradient
Scale ai Logo
LangChain Logo
divider

Introduction

This guide walks you through connecting Scale ai to LangChain 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 LangChain 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:
  • Get and set up your OpenAI and Composio API keys
  • Connect your Scale ai project to Composio
  • Create a Tool Router MCP session for Scale ai
  • Initialize an MCP client and retrieve Scale ai tools
  • Build a LangChain agent that can interact with Scale ai
  • Set up an interactive chat interface for testing

What is LangChain?

LangChain is a framework for developing applications powered by language models. It provides tools and abstractions for building agents that can reason, use tools, and maintain conversation context.

Key features include:

  • Agent Framework: Build agents that can use tools and make decisions
  • MCP Integration: Connect to external services through Model Context Protocol adapters
  • Memory Management: Maintain conversation history across interactions
  • Multi-Provider Support: Works with OpenAI, Anthropic, and other LLM providers

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 this tutorial, make sure you have:
  • Python 3.10 or higher installed on your system
  • A Composio account with an API key
  • An OpenAI API key
  • Basic familiarity with Python and async programming

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

pip install composio-langchain langchain-mcp-adapters langchain python-dotenv

Install the required packages for LangChain with MCP support.

What's happening:

  • composio-langchain provides Composio integration for LangChain
  • langchain-mcp-adapters enables MCP client connections
  • langchain is the core agent framework
  • python-dotenv loads environment variables

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_composio_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's API
  • COMPOSIO_USER_ID identifies the user for session management
  • OPENAI_API_KEY enables access to OpenAI's language models

Import dependencies

from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent
from dotenv import load_dotenv
from composio import Composio
import asyncio
import os

load_dotenv()
What's happening:
  • We're importing LangChain's MCP adapter and Composio SDK
  • The dotenv import loads environment variables from your .env file
  • This setup prepares the foundation for connecting LangChain with Scale ai functionality through MCP

Initialize Composio client

async def main():
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))

    if not os.getenv("COMPOSIO_API_KEY"):
        raise ValueError("COMPOSIO_API_KEY is not set")
    if not os.getenv("COMPOSIO_USER_ID"):
        raise ValueError("COMPOSIO_USER_ID is not set")
What's happening:
  • We're loading the COMPOSIO_API_KEY from environment variables and validating it exists
  • Creating a Composio instance that will manage our connection to Scale ai tools
  • Validating that COMPOSIO_USER_ID is also set before proceeding

Create a Tool Router session

# Create Tool Router session for Scale ai
session = composio.create(
    user_id=os.getenv("COMPOSIO_USER_ID"),
    toolkits=['scale_ai']
)

url = session.mcp.url
What's happening:
  • We're creating a Tool Router session that gives your agent access to Scale ai tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
  • This approach allows the agent to dynamically load and use Scale ai tools as needed

Configure the agent with the MCP URL

client = MultiServerMCPClient({
    "scale_ai-agent": {
        "transport": "streamable_http",
        "url": session.mcp.url,
        "headers": {
            "x-api-key": os.getenv("COMPOSIO_API_KEY")
        }
    }
})

tools = await client.get_tools()

agent = create_agent("gpt-5", tools)
What's happening:
  • We're creating a MultiServerMCPClient that connects to our Scale ai MCP server via HTTP
  • The client is configured with a name and the URL from our Tool Router session
  • get_tools() retrieves all available Scale ai tools that the agent can use
  • We're creating a LangChain agent using the GPT-5 model

Set up interactive chat interface

conversation_history = []

print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Scale ai related question or task to the agent.\n")

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ['exit', 'quit', 'bye']:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_history.append({"role": "user", "content": user_input})
    print("\nAgent is thinking...\n")

    response = await agent.ainvoke({"messages": conversation_history})
    conversation_history = response['messages']
    final_response = response['messages'][-1].content
    print(f"Agent: {final_response}\n")
What's happening:
  • We initialize an empty conversation_history list to maintain context across interactions
  • A while loop continuously accepts user input from the command line
  • When a user types a message, it's added to the conversation history and sent to the agent
  • The agent processes the request using the ainvoke() method with the full conversation history
  • Users can type 'exit', 'quit', or 'bye' to end the chat session gracefully

Run the application

if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • We call the main() function using asyncio.run() to start the application

Complete Code

Here's the complete code to get you started with Scale ai and LangChain:

from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent
from dotenv import load_dotenv
from composio import Composio
import asyncio
import os

load_dotenv()

async def main():
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    
    if not os.getenv("COMPOSIO_API_KEY"):
        raise ValueError("COMPOSIO_API_KEY is not set")
    if not os.getenv("COMPOSIO_USER_ID"):
        raise ValueError("COMPOSIO_USER_ID is not set")
    
    session = composio.create(
        user_id=os.getenv("COMPOSIO_USER_ID"),
        toolkits=['scale_ai']
    )

    url = session.mcp.url
    
    client = MultiServerMCPClient({
        "scale_ai-agent": {
            "transport": "streamable_http",
            "url": url,
            "headers": {
                "x-api-key": os.getenv("COMPOSIO_API_KEY")
            }
        }
    })
    
    tools = await client.get_tools()
  
    agent = create_agent("gpt-5", tools)
    
    conversation_history = []
    
    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Ask any Scale ai related question or task to the agent.\n")
    
    while True:
        user_input = input("You: ").strip()
        
        if user_input.lower() in ['exit', 'quit', 'bye']:
            print("\nGoodbye!")
            break
        
        if not user_input:
            continue
        
        conversation_history.append({"role": "user", "content": user_input})
        print("\nAgent is thinking...\n")
        
        response = await agent.ainvoke({"messages": conversation_history})
        conversation_history = response['messages']
        final_response = response['messages'][-1].content
        print(f"Agent: {final_response}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've successfully built a LangChain agent that can interact with Scale ai through Composio's Tool Router.

Key features of this implementation:

  • Dynamic tool loading through Composio's Tool Router
  • Conversation history maintenance for context-aware responses
  • Async Python provides clean, efficient execution of agent workflows
You can extend this further by adding error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-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

Vercel AI SDK

Vercel AI SDK

Use Scale ai MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Scale ai MCP with Mastra AI

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 LangChain?

Yes, you can. LangChain 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