How to integrate Polygon MCP with Vercel AI SDK v6

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Polygon logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Polygon to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Polygon agent that can show the latest closing price for btc-usd, list all stock tickers traded on nasdaq, get the crypto rsi for eth over 14 days through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Polygon account through Composio's Polygon MCP server.

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

Also integrate Polygon with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Polygon integration
  • Using Composio's Tool Router to dynamically load and access Polygon 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 Polygon MCP server, and what's possible with it?

The Polygon MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Polygon account. It provides structured and secure access to real-time and historical financial market data, so your agent can retrieve market status, analyze price indicators, track dividends, and monitor crypto and stock tickers on your behalf.

  • Market status and holiday tracking: Instantly check if U.S. exchanges are open or closed and retrieve upcoming market holidays or early closures to plan trading activities.
  • Comprehensive ticker retrieval: Ask your agent to fetch all available ticker symbols across asset classes, including stocks, crypto, forex, and options, filtered by market or exchange.
  • Crypto technical analysis: Have your agent calculate moving averages (EMA, SMA), MACD, and RSI indicators for specific cryptocurrencies to support informed trading decisions.
  • Daily and historical price fetching: Let your agent retrieve daily open/close prices, previous day’s close, or detailed price history for cryptocurrencies and stocks with just a prompt.
  • Dividend data extraction: Effortlessly access up-to-date corporate dividend information for stocks, enabling portfolio reviews and income analysis.

Supported Tools & Triggers

Tools
Get 10-K Filing SectionsTool to retrieve 10-K filing sections from the SEC.
Get AggregatesTool to fetch custom aggregate OHLCV bars for a stock.
Get All TickersTool to retrieve all ticker symbols across asset classes.
Get Condition CodesTool to retrieve a unified list of trade and quote condition codes and their definitions.
Get Crypto AggregatesTool to retrieve aggregate bars for a cryptocurrency over a time range.
Get Crypto All Tickers SnapshotTool to retrieve snapshots for all cryptocurrency tickers.
Get Crypto EMATool to calculate Exponential Moving Average (EMA) technical indicator for a crypto ticker.
Get Crypto Grouped DailyTool to retrieve daily grouped bars for all cryptocurrencies on a specified date.
Get Crypto Last TradeTool to retrieve the last trade for a specified cryptocurrency pair.
Get Crypto MACDTool to calculate Moving Average Convergence/Divergence (MACD) technical indicator for a crypto ticker.
Get Crypto Open/CloseTool to fetch daily open and close prices for a given crypto pair on a specified date.
Get Crypto Previous CloseTool to retrieve previous day’s close for a crypto ticker.
Get Crypto RSITool to calculate the Relative Strength Index (RSI) for a cryptocurrency ticker.
Get Crypto SMATool to calculate Simple Moving Average (SMA) technical indicator for a cryptocurrency ticker.
Get Crypto Ticker BookTool to retrieve the full L2 order book for a crypto ticker.
Get Crypto TradesTool to fetch historical trade data for a cryptocurrency ticker.
Get DividendsTool to retrieve dividend data for stocks.
Get Economy Inflation IndicatorsTool to retrieve key indicators of realized inflation including CPI and PCE price indexes.
Get Exponential Moving AverageTool to retrieve the Exponential Moving Average for a stock ticker.
Get SEC FilingTool to retrieve SEC filing details by filing ID.
Get SEC Filing FileTool to retrieve information about a specific SEC filing file.
Get Forex AggregatesTool to retrieve aggregate bars for a forex pair over a date range.
Get Forex EMATool to calculate Exponential Moving Average (EMA) technical indicator for a forex pair.
Get Forex Grouped Daily BarsTool to retrieve daily grouped OHLC bars for all forex currency pairs on a specified date.
Get Forex Historical QuotesTool to retrieve historical forex quotes for a currency pair over a time range.
Get Forex LocalesTool to list locales supported by Polygon's forex asset class.
Get Forex MACDTool to calculate Moving Average Convergence/Divergence (MACD) technical indicator for a forex pair.
Get Forex Previous CloseTool to retrieve previous day's close for a forex ticker.
Get Forex Real-Time Currency ConversionTool to convert amounts between currency pairs using real-time forex rates.
Get Forex RSITool to calculate the Relative Strength Index (RSI) technical indicator for a forex pair.
Get Forex SMATool to calculate Simple Moving Average (SMA) technical indicator for a forex pair.
Get Forex Snapshot LosersTool to retrieve the current snapshot of the top losers in the forex market.
Get Futures AggregatesTool to retrieve historical OHLCV aggregates for a futures contract.
Get Futures ProductsTool to retrieve a comprehensive list of futures products with advanced filtering.
Get Futures Product SchedulesTool to retrieve trading schedules for a futures product.
Get Futures QuotesTool to retrieve real-time quote data for a specified futures contract ticker.
Get Futures SchedulesTool to retrieve futures trading schedules.
Get Futures TradesTool to retrieve tick-level trade data for a specified futures contract.
Get Historic Forex TicksTool to get historic ticks for a currency pair on a specific date.
Get Inflation ExpectationsTool to retrieve inflation expectations data from the Federal Reserve based on Treasury yields and Cleveland Fed models.
Get IPO DataTool to retrieve comprehensive information on Initial Public Offerings (IPOs), including upcoming and historical events.
Get MACDTool to retrieve the Moving Average Convergence/Divergence (MACD) for a stock ticker.
Get Upcoming Market HolidaysTool to retrieve upcoming market holidays and half-day closures.
Get Market StatusTool to retrieve current market status.
Get Meta Conditions By TicktypeTool to retrieve condition code mappings for a specific tick type (trades or quotes).
Get NewsTool to retrieve recent news articles related to a ticker.
Get Stock Open/CloseTool to fetch daily open and close prices for a stock on a specific date.
Get Option Chain SnapshotTool to fetch a real-time snapshot of all option contracts for an underlying asset.
Get Options Contract OverviewTool to retrieve comprehensive details about a specific options contract including contract type, exercise style, expiration date, strike price, and underlying ticker.
Get Options Custom BarsTool to retrieve historical OHLC and volume data for options contracts over custom date ranges with configurable time windows.
Get Options EMATool to calculate Exponential Moving Average (EMA) technical indicator for an options ticker.
Get Options MACDTool to calculate Moving Average Convergence/Divergence (MACD) technical indicator for an options ticker.
Get Option SnapshotTool to retrieve a real-time snapshot for a single option contract.
Get Options RSITool to calculate Relative Strength Index (RSI) technical indicator for an options ticker.
Get Options SMATool to calculate Simple Moving Average (SMA) technical indicator for an options ticker.
Get Previous CloseTool to get previous trading day’s OHLC and volume for a stock.
Get reference exchangesTool to retrieve supported exchanges and their details.
Get reference marketsTool to retrieve all supported markets from Polygon.
Get Reference Ticker TypesTool to retrieve all ticker types supported by Polygon.
Get Related CompaniesTool to get a list of related companies for a ticker symbol based on various similarity metrics.
Get Risk CategoriesTool to retrieve risk factor taxonomy categories from SEC 10-K filings.
Get RSITool to retrieve the Relative Strength Index (RSI) for a stock ticker.
Get Short InterestTool to retrieve bi-monthly aggregated short interest data for stocks reported to FINRA.
Get Short VolumeTool to retrieve short volume data for stocks.
Get Simple Moving AverageTool to retrieve the Simple Moving Average (SMA) for any ticker (stocks, forex, crypto).
Get All Stock Tickers SnapshotTool to retrieve the current market snapshot for all stock tickers.
Get Stock Snapshot LosersTool to retrieve the current snapshot of the top losers in the U.
Get Stock Snapshot TickerTool to retrieve the current snapshot of a specific stock ticker.
Get Stock SplitsTool to retrieve stock split events.
Get Stock FinancialsTool to retrieve historical financial data for a stock ticker from SEC filings.
Get Stock FloatTool to retrieve stock float data showing the number and percentage of publicly tradable shares.
Get Stocks Balance SheetsTool to retrieve point-in-time balance sheet data including assets, liabilities, and equity from company SEC filings.
Get Stocks Cash Flow StatementsTool to retrieve historical cash flow statement data from company SEC filings across quarterly, annual, and TTM frequencies.
Get Stocks Custom BarsTool to retrieve aggregated historical OHLC and volume data for a stock over custom date ranges with configurable time windows.
Get Stocks Daily Market SummaryTool to retrieve daily OHLC, volume, and VWAP data for all U.
Get Stock Splits by TickerTool to retrieve historical stock splits for a specific ticker symbol.
Get Simple Moving Average (SMA)Tool to fetch Simple Moving Average (SMA) for a given stock ticker.
Get Ticker Company DetailsTool to retrieve detailed company information for a stock ticker.
Get Ticker DetailsTool to retrieve detailed information for a ticker.
Get Ticker Details (vX)Tool to retrieve comprehensive details for a specific ticker symbol using Polygon's vX API.
Get Ticker EventsTool to retrieve corporate events for a specific ticker.
Get Ticker TypesTool to retrieve all ticker types supported by Polygon.
Get Treasury YieldsTool to retrieve historical U.
Get V1 Meta Crypto ExchangesTool to retrieve a list of cryptocurrency exchanges using the legacy v1 API.
Last Quote for a SymbolTool to retrieve the last quote tick for a given stock symbol.
Last Trade for a Currency PairTool to retrieve the last trade tick for a currency pair in the forex market.
List SEC Filing FilesTool to retrieve files associated with an SEC filing.
List Options ContractsTool to list and filter options contracts by underlying ticker, type, expiration, strike, and more.
List SEC FilingsTool to retrieve SEC filings from Polygon.

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: ["polygon"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Polygon 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 Polygon-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 Polygon 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 polygon, 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 Polygon 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 Polygon 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: ["polygon"],
  });

  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 polygon, 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 Polygon 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 Polygon MCP Agent with another framework

FAQ

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

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

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

Yes, absolutely. You can configure which Polygon 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 Polygon 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.