How to integrate Finage 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

Finage logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Finage to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Finage agent that can show real-time quote for aapl stock, summarize today's news for tsla, get last week's price history for msft through natural language commands.

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

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

Also integrate Finage with

TL;DR

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

The Finage MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Finage account. It provides structured and secure access to real-time and historical financial market data, so your agent can perform actions like fetching live stock quotes, analyzing market trends, retrieving news, and monitoring market status on your behalf.

  • Real-time stock quotes and market snapshots: Instantly get up-to-date price quotes, volume, bid/ask details, or aggregate snapshots for one or multiple stocks at once.
  • Historical and end-of-day data retrieval: Have your agent pull detailed historical or end-of-day OHLCV data for any stock symbol to analyze trends or generate reports.
  • Market news and updates analysis: Stay on top of the latest financial news, filtered by specific stocks, to inform investment decisions or research market events.
  • Market status and exchange monitoring: Check if major stock markets are open or closed, review trading hours, and plan automated trades based on real-time market status.
  • Tick-by-tick and previous close data access: Dive into granular tick-level trade data or review the previous day's close for any symbol to support high-frequency trading or day-over-day analysis.

Supported Tools & Triggers

Tools
Convert CryptocurrenciesTool to convert cryptocurrencies using real-time exchange rates from the Finage API.
Convert CurrencyTool to convert currencies using real-time forex exchange rates from Finage API.
Get US Treasury Bond RateRetrieve the current interest rate for a US Treasury bond by maturity.
Get Country DetailsTool to retrieve detailed information about a country including currency, phone code, and flag.
Get Crypto AggregatesTool to retrieve aggregated OHLCV time-series data for cryptocurrency pairs over specified time periods.
Get Crypto DetailTool to get detailed fundamental information about a cryptocurrency including description, developers, website, social media links, and technical details.
Get Detailed Crypto InformationThis tool fetches detailed cryptocurrency information including current price, price changes, volume, market cap, and historical highs/lows for a specific cryptocurrency pair.
Get Crypto Last QuoteTool to get the last quote with bid/ask prices in real-time for a cryptocurrency pair.
Get Crypto Last TradeTool to get the latest trade information and prices in real-time for a cryptocurrency pair.
Get Crypto NewsTool to retrieve real-time and historical news for cryptocurrency markets with fast In-Memory Cache Engine.
Get Crypto Previous Close DataTool to get the previous day's closing data for a cryptocurrency pair.
Get Crypto SnapshotTool to get a comprehensive snapshot of cryptocurrency market data with latest quotes and trades in one request.
Get Currency DetailTool to get detailed information about a forex currency pair including currency codes and country flags.
Get Forex Last QuoteTool to get the latest real-time bid/ask quote for a forex pair or metal (e.
Get Forex Last TradeTool to get the last trade information for a forex currency pair.
Get Forex Market AggregatesTool to retrieve aggregated OHLCV (Open, High, Low, Close, Volume) data for forex and metal pairs over specified time periods.
Get Forex NewsTool to retrieve real-time and historical news for forex markets from Finage's API.
Get Forex Previous Close DataTool to get the previous day's closing data for a forex currency pair.
Get Forex SnapshotTool to get a comprehensive snapshot of forex market data with latest quotes and trades in one request.
Get Most Active US StocksTool to get a list of the most actively traded US stocks.
Get SEC RSS FeedTool to retrieve the SEC RSS feed for recent EDGAR filings.
Get Sector PerformanceTool to retrieve performance metrics across US market sectors.
Get Stock Company DetailsTool to retrieve detailed company information and stock fundamentals for a given ticker symbol.
Get Stock Last QuoteFetches the latest single-tick quote for a stock symbol, returning a JSON object with fields: symbol, ask, bid, asize, bsize, and timestamp.
Get Stock Last TradeTool to get the most recent trade information for a specified US stock symbol.
Get Stock Market AggregatesRetrieves aggregated OHLCV (Open, High, Low, Close, Volume) data for US stocks only.
Get Stock Market NewsThis tool retrieves the latest market news from Finage's API.
Get Stock Market StatusTool to check if stock, forex, and crypto markets are open, closed, or in extended hours.
Get Stock Previous Close DataThis tool retrieves the previous day's closing data for a specific stock symbol.
Get Stock SnapshotTool to get comprehensive snapshot of all US stock market data including latest quotes and trades with one single API request.
Get Technical IndicatorsTool to get technical indicators and signals for stocks from Finage API.
Get Top Gaining US StocksTool to get list of top gaining US stocks by percentage change.
Get Top Losing US StocksTool to get list of top losing US stocks by percentage change.
List Cryptocurrencies by Market CapTool to get a list of all available cryptocurrencies ranked by market capitalization.
List Symbols by Market TypeTool to get a paginated list of all available symbols for a specified market type (us-stock, ca-stock, in-stock, ru-stock, forex, crypto, index).
Search CountryTool to search for countries by name and retrieve their details including country code, currency, flag, and phone code.
Search CryptocurrencyTool to search for cryptocurrencies by name or symbol.
Search CurrencyTool to search for currency pairs and forex symbols by currency code or partial match.
Search Market for StocksTool to search for stocks in a specific market by company name or 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: ["finage"],
  });

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

  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 finage, 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 Finage 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 Finage MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Finage MCP with ChatGPT

Antigravity logo

Antigravity

Use Finage MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Finage MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Finage MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Finage MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Finage MCP with Claude Cowork

Codex logo

Codex

Use Finage MCP with Codex

Cursor logo

Cursor

Use Finage MCP with Cursor

OpenClaw logo

OpenClaw

Use Finage MCP with OpenClaw

Hermes logo

Hermes

Use Finage MCP with Hermes

CLI logo

CLI

Use Finage MCP with CLI

Google ADK logo

Google ADK

Use Finage MCP with Google ADK

LangChain logo

LangChain

Use Finage MCP with LangChain

Mastra AI logo

Mastra AI

Use Finage MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Finage MCP with LlamaIndex

CrewAI logo

CrewAI

Use Finage MCP with CrewAI

OpenCode logo

OpenCode

Use Finage MCP with OpenCode

VS Code logo

VS Code

Use Finage MCP with VS Code

FAQ

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

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

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

Yes, absolutely. You can configure which Finage 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 Finage 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↗