How to integrate Coinranking MCP with CrewAI

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

Introduction

This guide walks you through connecting Coinranking to CrewAI using the Composio tool router. By the end, you'll have a working Coinranking agent that can show top trending cryptocurrencies today, get bitcoin price history for last month, list coins with market cap over $1b, summarize global crypto market stats now through natural language commands.

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

The Coinranking MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Coinranking account. It provides structured and secure access to real-time and historical cryptocurrency market data, so your agent can perform actions like tracking prices, analyzing trends, fetching coin stats, and surfacing trending cryptocurrencies on your behalf.

  • Real-time coin price tracking: Instantly access up-to-date prices for thousands of cryptocurrencies, letting your agent monitor the market or retrieve coin values on demand.
  • Historical performance analysis: Retrieve and analyze historical price data for any coin, so your agent can chart trends and compare past performances.
  • Global market overview: Get comprehensive statistics about the entire crypto market, including total market cap, volume, and dominance, all via your agent.
  • Discover trending assets: Surface the most popular and trending coins based on user engagement, helping your agent highlight coins gaining traction right now.
  • Reference currencies and tags management: Let your agent fetch supported fiat and crypto reference currencies, and retrieve all canonical tags for advanced filtering and categorization.

Supported Tools & Triggers

Tools
Get Coin HistoryTool to retrieve historical price data for a specific coin over a time period.
Get CoinsTool to retrieve a list of all coins with optional filters and pagination.
Get Reference CurrenciesTool to retrieve a list of all reference currencies with optional pagination.
Get Global Crypto Market StatsTool to retrieve global cryptocurrency market statistics.
Get TagsTool to fetch all coin tags.
Get Trending CoinsTool to retrieve a list of trending coins ranked by user engagement and popularity.

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 Coinranking 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 Coinranking 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 Coinranking MCP URL

Create a Composio Tool Router session for Coinranking

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["coinranking"],
)
url = session.mcp.url
What's happening:
  • You create a Coinranking only session through Composio
  • Composio returns an MCP HTTP URL that exposes Coinranking 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="Coinranking Assistant",
    goal="Help users interact with Coinranking through natural language commands",
    backstory=(
        "You are an expert assistant with access to Coinranking tools. "
        "You can perform various Coinranking 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 Coinranking 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 Coinranking 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 Coinranking 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_coinranking_agent.py

Complete Code

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

python
# file: crewai_coinranking_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 Coinranking session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["coinranking"],
    )
    url = session.mcp.url

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

    # Create Coinranking assistant agent
    toolkit_agent = Agent(
        role="Coinranking Assistant",
        goal="Help users interact with Coinranking through natural language commands",
        backstory=(
            "You are an expert assistant with access to Coinranking tools. "
            "You can perform various Coinranking 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 Coinranking 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 Coinranking 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 Coinranking through Composio's Tool Router. The agent can perform Coinranking 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 Coinranking MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Coinranking MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Coinranking MCP with Claude Agent SDK

Google ADK

Google ADK

Use Coinranking MCP with Google ADK

LangChain

LangChain

Use Coinranking MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Coinranking MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Coinranking MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Coinranking MCP with LlamaIndex

FAQ

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

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

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

Yes, absolutely. You can configure which Coinranking 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 Coinranking 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