How to integrate Bigml MCP with CrewAI

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Bigml logo
CrewAI logo
divider

Introduction

This guide walks you through connecting Bigml to CrewAI using the Composio tool router. By the end, you'll have a working Bigml agent that can create a new bigml project for customer data, list all correlations available in your account, get details for a specific bigml project through natural language commands.

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

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

Also integrate Bigml with

TL;DR

Here's what you'll learn:
  • Get a Composio API key and configure your Bigml connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Bigml
  • Build a conversational loop where your agent can execute Bigml operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

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

The Bigml MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Bigml account. It provides structured and secure access to your machine learning environment, so your agent can perform actions like creating projects, managing data connectors, inspecting resources, and analyzing correlations on your behalf.

  • Project creation and organization: Easily direct your agent to create new projects to group related BigML resources for streamlined workflows.
  • External data connector management: Have your agent set up and retrieve external connectors to bring in data from external sources and databases.
  • Resource inspection and retrieval: Let your agent fetch detailed metadata about projects or connectors, helping you monitor and audit your ML assets.
  • Automated project cleanup: Instruct your agent to delete obsolete or unused projects, ensuring your workspace stays organized and efficient.
  • Correlation browsing and analysis: Ask your agent to list and paginate correlation resources, uncovering relationships among your datasets for deeper insights.

Supported Tools & Triggers

Tools
Create External ConnectorTool to create a new external connector for data sources.
Create ProjectTool to create a new project.
Delete ProjectTool to delete an existing project.
Get ConfigurationRetrieves complete details of a BigML configuration by its ID to get stored parameters.
Get External ConnectorRetrieves complete details of a BigML external connector by its ID.
Get ProjectTool to retrieve details of a project by ID.
Get SourceRetrieves complete details of a BigML source by its ID.
List Anomaly DetectorsTool to list anomaly detector resources in your account.
List Anomaly ScoresTool to list anomaly score resources.
List AssociationsTool to list association resources.
List Association SetsTool to list association set resources in your account.
List Batch Anomaly ScoresTool to list batch anomaly score resources.
List Batch CentroidsTool to list all batch centroid resources in your account with support for filtering, ordering, and pagination.
List Batch PredictionsTool to list batch prediction resources.
List Batch ProjectionsTool to list batch projection resources with support for filtering, ordering, and pagination.
List Batch Topic DistributionsTool to list batch topic distribution resources.
List CentroidsTool to list centroid resources.
List ClustersTool to list cluster resources with support for filtering, ordering, and pagination.
List CompositesTool to list composite source resources.
List ConfigurationsTool to list all configuration resources in your account.
List CorrelationsTool to list correlation resources.
List DatasetsTool to list dataset resources.
List DeepnetsTool to list deep neural network resources.
List EnsemblesTool to list ensemble resources with filtering, ordering, and pagination support.
List EvaluationsTool to list evaluation resources.
List ExecutionsTool to list execution resources.
List ForecastsTool to list forecast resources.
List FusionsTool to list fusion resources.
List LibrariesTool to list WhizzML library resources.
List Linear RegressionsTool to list linear regression resources.
List Logistic RegressionsTool to list logistic regression resources.
List ModelsTool to list model resources.
List OptiMLsTool to list OptiML resources in your account.
List PCAsTool to list PCA resources.
List PredictionsTool to list prediction resources.
List ProjectionsTool to list projection resources with support for filtering, ordering, and pagination.
List ProjectsTool to list all project resources in your account with support for filtering, ordering, and pagination.
List SamplesTool to list sample resources.
List ScriptsTool to list WhizzML script resources.
List SourcesTool to list source resources in your account.
List Statistical TestsTool to list statistical test resources.
List Time SeriesTool to list time series resources.
List Topic DistributionsTool to list topic distribution resources.
List Topic ModelsTool to list topic model resources.
Update SourceTool to update a source's name, description, tags, or parsing configuration.

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:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Bigml connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

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

bash
pip install composio crewai crewai-tools[mcp] python-dotenv
What's happening:
  • composio connects your agent to Bigml via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools[mcp] includes MCP helpers
  • python-dotenv loads environment variables from .env

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
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 with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model

Import dependencies

python
import os
from composio import Composio
from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
import dotenv

dotenv.load_dotenv()

COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Bigml MCP URL

Create a Composio Tool Router session for Bigml

python
composio_client = Composio(api_key=COMPOSIO_API_KEY)
session = composio_client.create(user_id=COMPOSIO_USER_ID, toolkits=["bigml"])

url = session.mcp.url
What's happening:
  • You create a Bigml only session through Composio
  • Composio returns an MCP HTTP URL that exposes Bigml tools

Initialize the MCP Server

python
server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users search the internet effectively",
        backstory="You are a helpful assistant with access to search tools.",
        tools=tools,
        verbose=False,
        max_iter=10,
    )
What's Happening:
  • Server Configuration: The code sets up connection parameters including the MCP server URL, streamable HTTP transport, and Composio API key authentication.
  • MCP Adapter Bridge: MCPServerAdapter acts as a context manager that converts Composio MCP tools into a CrewAI-compatible format.
  • Agent Setup: Creates a CrewAI Agent with a defined role (Search Assistant), goal (help with internet searches), and access to the MCP tools.
  • Configuration Options: The agent includes settings like verbose=False for clean output and max_iter=10 to prevent infinite loops.
  • Dynamic Tool Usage: Once created, the agent automatically accesses all Composio Search tools and decides when to use them based on user queries.

Create a CLI Chatloop and define the Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")

conversation_context = ""

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

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

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Conversation history:\n{conversation_context}\n\n"
            f"Current request: {user_input}"
        ),
        expected_output="A helpful response addressing the user's request",
        agent=agent,
    )

    crew = Crew(agents=[agent], tasks=[task], verbose=False)
    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's Happening:
  • Interactive CLI Setup: The code creates an infinite loop that continuously prompts for user input and maintains the entire conversation history in a string variable.
  • Input Validation: Empty inputs are ignored to prevent processing blank messages and keep the conversation clean.
  • Context Building: Each user message is appended to the conversation context, which preserves the full dialogue history for better agent responses.
  • Dynamic Task Creation: For every user input, a new Task is created that includes both the full conversation history and the current request as context.
  • Crew Execution: A Crew is instantiated with the agent and task, then kicked off to process the request and generate a response.
  • Response Management: The agent's response is converted to a string, added to the conversation context, and displayed to the user, maintaining conversational continuity.

Complete Code

Here's the complete code to get you started with Bigml and CrewAI:

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter
from composio import Composio
from dotenv import load_dotenv
import os

load_dotenv()

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_API_KEY is not set in the environment.")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment.")

# Initialize Composio and create a session
composio = Composio(api_key=COMPOSIO_API_KEY)
session = composio.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["bigml"],
)
url = session.mcp.url

# Configure LLM
llm = LLM(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY"),
)

server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users with internet searches",
        backstory="You are an expert assistant with access to Composio Search tools.",
        tools=tools,
        llm=llm,
        verbose=False,
        max_iter=10,
    )

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

    conversation_context = ""

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

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

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Conversation history:\n{conversation_context}\n\n"
                f"Current request: {user_input}"
            ),
            expected_output="A helpful response addressing the user's request",
            agent=agent,
        )

        crew = Crew(agents=[agent], tasks=[task], verbose=False)
        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

Conclusion

You now have a CrewAI agent connected to Bigml through Composio's Tool Router. The agent can perform Bigml operations through natural language commands.

Next steps:

  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations

How to build Bigml MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Bigml MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Bigml MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Bigml MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Bigml MCP with Claude Cowork

Codex logo

Codex

Use Bigml MCP with Codex

OpenClaw logo

OpenClaw

Use Bigml MCP with OpenClaw

Hermes logo

Hermes

Use Bigml MCP with Hermes

CLI logo

CLI

Use Bigml MCP with CLI

Google ADK logo

Google ADK

Use Bigml MCP with Google ADK

LangChain logo

LangChain

Use Bigml MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Bigml MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Bigml MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Bigml MCP with LlamaIndex

FAQ

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

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

Can I use Tool Router MCP with CrewAI?

Yes, you can. CrewAI 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 Bigml tools.

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

Yes, absolutely. You can configure which Bigml 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 Bigml 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.

Get started for freeGet a demo↗