How to integrate Twelve data MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Twelve data Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Twelve data to AutoGen using the Composio tool router. By the end, you'll have a working Twelve data agent that can list all supported cryptocurrencies today, convert 100 usd to eur right now, show recent dividend payouts for aapl, get top etfs sorted by total assets through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Twelve data account through Composio's Twelve data 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
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Twelve data
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Twelve data tools
  • Run a live chat loop where you ask the agent to perform Twelve data operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

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

The Twelve data MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Twelve Data account. It provides structured and secure access to real-time and historical financial market data, so your agent can retrieve stock prices, analyze dividend and earnings history, explore ETFs, and perform currency conversions on your behalf.

  • Comprehensive market data access: Instantly pull up-to-date information on stocks, forex, cryptocurrencies, commodities, and indices to support analysis or decision-making.
  • Dividend and earnings insights: Retrieve detailed dividend payout history and earnings reports, including EPS estimates, actuals, and trend analysis for specific companies.
  • ETF exploration and categorization: Ask your agent to fetch directories of ETFs, sort by assets, family, or market, and explore various ETF types for in-depth portfolio research.
  • Real-time currency conversion: Effortlessly convert amounts between currencies using live exchange rates for accurate financial planning and reporting.
  • Cryptocurrency and commodity discovery: List all supported cryptocurrencies and commodities, helping you quickly identify available assets for further analysis or trading strategies.

Supported Tools & Triggers

Tools
List CommoditiesTool to retrieve a list of supported commodities.
List CryptocurrenciesTool to list all supported cryptocurrencies.
Currency ConversionTool to convert an amount from one currency to another.
DividendsTool to retrieve dividend payout history for a specified symbol.
EarningsTool to retrieve earnings data including eps estimates and actuals.
EPS RevisionsTool to provide analysts’ revisions of a company’s future eps over the last week and month.
EPS TrendTool to retrieve historical eps trends for a specified company.
ETFS DirectoryTool to fetch a daily updated list of exchange-traded funds sorted by total assets.
ETFS FamilyTool to fetch a comprehensive list of etfs by family.
Get ETF TypesTool to retrieve etf categories by market, including types like 'equity precious metals'.
List supported exchangesTool to retrieve a list of supported exchanges.
List supported forex pairsTool to retrieve a list of all supported forex currency pairs.
List market indicesTool to retrieve a list of market indices.
Mutual Funds FamilyTool to list all available mutual fund families.
Mutual Funds ListTool to retrieve a daily updated list of mutual funds sorted by total assets.
Options ChainTool to retrieve the options chain for a given symbol and optional expiration date.
Options ExpirationTool to retrieve available option expiration dates.
QuoteTool to retrieve the latest market data for a specified symbol.
List StocksTool to retrieve a list of stocks.
Symbol SearchTool to search for financial instruments by symbol or company name.
Technical IndicatorsTool to fetch time-series data for a specific technical indicator.
Time SeriesTool to retrieve historical and real-time time series data for a specified symbol.

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

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Twelve data account you can connect to Composio
  • Some basic familiarity with Autogen and Python async

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 python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Twelve data via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Twelve data connections to use

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Twelve data session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["twelve_data"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Twelve data tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Twelve data assistant agent with MCP tools
    agent = AssistantAgent(
        name="twelve_data_assistant",
        description="An AI assistant that helps with Twelve data operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Twelve data tools from the workbench

Run the interactive chat loop

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

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

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

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Twelve data tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Twelve data and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

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

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Twelve data assistant agent with MCP tools
        agent = AssistantAgent(
            name="twelve_data_assistant",
            description="An AI assistant that helps with Twelve data operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

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

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

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

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

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

Conclusion

You now have an Autogen assistant wired into Twelve data through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Twelve data, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Twelve data MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Twelve data MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Twelve data MCP with Claude Agent SDK

Google ADK

Google ADK

Use Twelve data MCP with Google ADK

LangChain

LangChain

Use Twelve data MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Twelve data MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Twelve data MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Twelve data MCP with LlamaIndex

CrewAI

CrewAI

Use Twelve data MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Twelve data MCP?

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

Can I use Tool Router MCP with Autogen?

Yes, you can. Autogen 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 Twelve data tools.

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

Yes, absolutely. You can configure which Twelve data 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 Twelve data 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