How to integrate Kaleido MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Kaleido Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Kaleido to CrewAI using the Composio tool router. By the end, you'll have a working Kaleido agent that can list all api keys for my organization, create a new api key for our consortium, show all event streams configured in this environment, retrieve memberships for the current user through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Kaleido account through Composio's Kaleido 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 a Composio API key and configure your Kaleido connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Kaleido
  • Build a conversational loop where your agent can execute Kaleido 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 Kaleido MCP server, and what's possible with it?

The Kaleido MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Kaleido account. It provides structured and secure access to your blockchain environment, so your agent can perform actions like managing organizations, handling API keys, retrieving memberships, and monitoring event streams on your behalf.

  • Organization and consortium management: Let your agent list, retrieve, and manage organizations and consortia that you have access to—making it easy to keep your blockchain networks organized.
  • API key lifecycle control: Effortlessly create, retrieve, and delete API keys for your organization, so you can handle credential management without manual steps.
  • Membership and access insights: Quickly fetch details about user memberships and organizational access, helping you stay on top of roles and permissions in your blockchain environment.
  • Event stream monitoring: Retrieve and review all event streams configured in your environment, making it simple to keep tabs on real-time blockchain activity.
  • App2App and credential retrieval: Ask your agent to list App2App runtimes and fetch application credentials for specific environments, streamlining application integration and deployment.

Supported Tools & Triggers

Tools
Add Organization Identity ProofTool to add an identity proof to an organization.
Create API KeyTool to create a new API key for an organization.
Delete API KeyTool to delete a specific API key.
Get API KeysTool to retrieve all API keys associated with the organization.
Get App2App RuntimesTool to retrieve App2App runtimes by listing all services and filtering where service == 'app2app'.
Get Application CredentialsTool to retrieve application credentials for a specific environment.
Get ConsortiaTool to retrieve all consortia associated with the organization.
Get Event StreamsTool to list all event streams configured in the environment.
Get MembershipsTool to retrieve all memberships for the current user.
Get OrganizationsTool to retrieve all organizations that the authenticated user has access to.
Get RegionsTool to retrieve the list of deployment zones and endpoints.
Get ReleasesTool to retrieve current and historical versions of node software.
Get RolesTool to retrieve all roles of an organization.
Get ServicesTool to retrieve all services the current user owns or can see.
Get Token Factory TokensTool to retrieve all tokens managed by the Token Factory.
Get Wallet Account NonceTool to retrieve the current nonce of a specific HD wallet account.
Get WalletsTool to retrieve HD wallet IDs hosted in the service.

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:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Kaleido 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 python-dotenv
What's happening:
  • composio connects your agent to Kaleido via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools 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
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
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 Kaleido MCP URL

Create a Composio Tool Router session for Kaleido

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["kaleido"],
)
url = session.mcp.url
What's happening:
  • You create a Kaleido only session through Composio
  • Composio returns an MCP HTTP URL that exposes Kaleido tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Kaleido Assistant",
    goal="Help users interact with Kaleido through natural language commands",
    backstory=(
        "You are an expert assistant with access to Kaleido tools. "
        "You can perform various Kaleido operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Kaleido MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Kaleido operations.\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"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Kaleido related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_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:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_kaleido_agent.py

Complete Code

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

python
# file: crewai_kaleido_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Kaleido session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["kaleido"],
    )
    url = session.mcp.url

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

    # Create Kaleido assistant agent
    toolkit_agent = Agent(
        role="Kaleido Assistant",
        goal="Help users interact with Kaleido through natural language commands",
        backstory=(
            "You are an expert assistant with access to Kaleido tools. "
            "You can perform various Kaleido operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Kaleido operations.\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"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Kaleido related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

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

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Kaleido through Composio's Tool Router. The agent can perform Kaleido 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 Kaleido MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Kaleido MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Kaleido MCP with Claude Agent SDK

Google ADK

Google ADK

Use Kaleido MCP with Google ADK

LangChain

LangChain

Use Kaleido MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Kaleido MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Kaleido MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Kaleido MCP with LlamaIndex

FAQ

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

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

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

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

Used by agents from

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