How to integrate Twelve data MCP with Vercel AI SDK v6

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

30 min · no commitment · see it on your stack

Twelve data logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Twelve data to Vercel AI SDK v6 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 through natural language commands.

This guide will help you understand how to give your Vercel AI SDK 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.

Also integrate Twelve data with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Twelve data integration
  • Using Composio's Tool Router to dynamically load and access Twelve data tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

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
Cash FlowTool to get company cash flow statement.
Consolidated Cash FlowTool to get raw consolidated cash flow statements.
List CommoditiesTool to retrieve a list of supported commodities.
Correlation CoefficientTool to fetch Pearson correlation coefficient between two series over a period.
List CountriesTool to retrieve a list of countries with ISO codes, names, capitals, and currencies.
Cross ListingsTool to retrieve cross-listed symbols for a security across multiple exchanges.
List CryptocurrenciesTool to list all supported cryptocurrencies.
List Cryptocurrency ExchangesTool to list supported cryptocurrency exchanges.
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 EPS trend estimates 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'.
ETF WorldTool to fetch comprehensive ETF analytics (summary, performance, risk, composition).
ETF World CompositionTool to fetch global ETF composition details including sector, country, asset allocations, top holdings, and bond metrics.
ETF World RiskTool to get global ETF risk metrics.
List supported exchangesTool to retrieve a list of supported exchanges.
List supported forex pairsTool to retrieve a list of all supported forex currency pairs.
Get AD IndicatorTool to retrieve Accumulation/Distribution (AD) indicator data for a financial instrument.
Get API UsageTool to retrieve your current plan and remaining API credits.
Get APO (Absolute Price Oscillator)Tool to calculate the Absolute Price Oscillator (APO) for a financial instrument.
Get Aroon IndicatorTool to retrieve Aroon Indicator data for identifying market trends.
Balance SheetTool to retrieve a company's balance sheet (assets, liabilities, equity).
Balance Sheet ConsolidatedTool to get raw consolidated balance sheet data (assets, liabilities, equity) for a company.
Get Bollinger BandsTool to calculate Bollinger Bands (BBANDS) for a financial instrument.
Get BondsTool to retrieve a daily updated list of available bonds (fixed income securities).
Get CCITool to retrieve Commodity Channel Index (CCI) values for a specified security.
Get Ceiling (CEIL)Tool to retrieve the Ceiling (CEIL) transformation for a time series.
Get Chande Momentum OscillatorTool to retrieve Chande Momentum Oscillator (CMO) data for a security.
Get Detrended Price OscillatorTool to calculate the Detrended Price Oscillator (DPO) for a specified financial instrument.
Get Earliest TimestampTool to return the first available timestamp for a symbol and interval.
Get End of Day PriceTool to retrieve end of day (EOD) closing price and metadata for a financial instrument.
Global ETF PerformanceTool to get global ETF performance metrics (trailing and annual returns).
Get exchange scheduleTool to get trading sessions and hours for exchanges.
Get Fund HoldersTool to retrieve mutual fund holders for a company.
Get FundsTool to fetch a daily updated list of available investment funds.
Get Heikin Ashi CandlesTool to retrieve Heikin Ashi candlestick data that smooths price action by averaging values.
Get HLC3 AverageTool to calculate the High, Low, Close Average (HLC3) for a security over a specified period.
Get Hilbert Transform Sine WaveTool to fetch Hilbert Transform Sine Wave (HT_SINE) data for an instrument.
Get Ichimoku Cloud IndicatorTool to retrieve Ichimoku Kinko Hyo indicator data for analyzing trend direction, support/resistance levels, and trading opportunities.
Income StatementTool to retrieve a company's income statement data (annual or quarterly).
Insider TransactionsREQUIRES PRO, ULTRA, OR ENTERPRISE PLAN.
Get Available IntervalsTool to retrieve a list of available time intervals supported by the API.
Get Keltner ChannelTool to retrieve Keltner Channel indicator data for volatility-based technical analysis.
Key ExecutivesREQUIRES ULTRA OR ENTERPRISE PLAN.
Get Last ChangeTool to retrieve the latest update timestamps for a fundamentals dataset.
Get Linear Regression AngleTool to calculate the linear regression angle for a given time series of stock prices.
Get Linear Regression InterceptTool to calculate the y-intercept of a linear regression line for a given dataset.
Get Linear Regression SlopeTool to calculate the linear regression slope for a given dataset over a specified period.
Get Base-10 Logarithm (LOG10)Tool to compute the base-10 logarithm (LOG10) of a specified input value.
Get LogoTool to retrieve official logo URLs for a symbol.
Get MACDTool to calculate the Moving Average Convergence Divergence (MACD) for a specified financial instrument.
Get MAMATool to fetch MESA Adaptive Moving Average (MAMA) indicator data.
Market MoversTool to retrieve a snapshot of top gainers or losers for a specified market.
Get Market StateTool to report current open/closed status for exchanges.
Get Maximum ValueTool to calculate and return the highest value within a specified data series over a given period.
Get McGinley Dynamic IndicatorTool to calculate the McGinley Dynamic indicator, which provides a refined moving average that adapts to market volatility.
Get Median PriceTool to calculate and retrieve the Median Price (MEDPRICE) technical indicator for a security.
Get Minus Directional IndicatorTool to calculate and return the Minus Directional Indicator (MINUS_DI) for a security.
Global Mutual Fund PerformanceTool to get global mutual fund performance metrics (trailing, annual, quarterly, load-adjusted returns).
Mutual Funds World RiskTool to fetch global mutual fund risk metrics.
Global Mutual Fund SummaryTool to retrieve a global mutual fund summary snapshot.
Global Mutual Fund SustainabilityTool to get global mutual fund sustainability and ESG metrics.
Get Plus Directional IndicatorTool to fetch the Plus Directional Indicator (PLUS_DI) time series data for a security.
Get PriceTool to retrieve the latest market price for a specified financial instrument.
Price TargetTool to fetch analysts' price target dataset for equities.
Get ProfileTool to retrieve company profile.
RecommendationsRetrieve aggregated analyst recommendations for a stock.
Get Rate of Change (ROC)Tool to retrieve Rate of Change (ROC) indicator data for a security.
Get ROCP (Rate of Change Percentage)Tool to calculate and return the Rate of Change Percentage (ROCP) for a financial security.
Get ROCR100Tool to calculate the Rate of Change Ratio 100 (ROCR100) for a security.
Get Relative VolumeTool to fetch relative volume (RVOL) data for a security.
Stock SplitsTool to retrieve historical stock split events.
Splits CalendarTool to retrieve a calendar of stock split events.
Get StatisticsTool to retrieve key company statistics including valuation and financial overview.
Get Stochastic RSITool to calculate the Stochastic Relative Strength Index (Stochastic RSI) for a specified financial instrument.
Get Summation (SUM)Tool to calculate the cumulative total (Summation) of a specified data series over a defined time period.
Get Technical Indicators ListTool to retrieve a comprehensive list of available technical indicators.
Get TEMA (Triple Exponential Moving Average)Tool to calculate the Triple Exponential Moving Average (TEMA) for a financial instrument.
Get Variance (VAR)Tool to calculate the statistical variance of a financial data series.
Get Weighted Close PriceTool to calculate and retrieve the Weighted Close Price (WCLPRICE) for a security.
Get Weighted Moving Average (WMA)Tool to calculate and retrieve the Weighted Moving Average (WMA) for a security over a specified period.
List market indicesTool to retrieve a list of market indices.
Institutional HoldersTool to retrieve institutional holders positions for a company.
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.
Mutual Funds World CompositionTool to fetch global mutual fund portfolio composition including sectors, asset allocation, top holdings, and bond metrics.
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 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 you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key

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 required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["twelve_data"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Twelve data tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Twelve data-related tools through the MCP protocol

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Twelve data tools that the agent can use

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to twelve_data, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Twelve data tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Twelve data and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["twelve_data"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to twelve_data, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Twelve data agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

How to build Twelve data MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Twelve data MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Twelve data MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Twelve data MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Twelve data MCP with Claude Cowork

Codex logo

Codex

Use Twelve data MCP with Codex

OpenClaw logo

OpenClaw

Use Twelve data MCP with OpenClaw

Hermes logo

Hermes

Use Twelve data MCP with Hermes

CLI logo

CLI

Use Twelve data MCP with CLI

Google ADK logo

Google ADK

Use Twelve data MCP with Google ADK

LangChain logo

LangChain

Use Twelve data MCP with LangChain

Mastra AI logo

Mastra AI

Use Twelve data MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Twelve data MCP with LlamaIndex

CrewAI logo

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 Vercel AI SDK v6?

Yes, you can. Vercel AI SDK v6 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
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↗