// vercel ai sdk

Market data tools for
the Vercel AI SDK.

Register TickerAPI methods as AI SDK tools. Your language model gets access to live market summaries, scans, and comparisons — grounding financial responses in real data.

try for free read the docs

// setup

Install the dependencies.

Add the TickerAPI SDK alongside the Vercel AI SDK.

terminal

npm install tickerapi ai @ai-sdk/openai

Set TICKERAPI_KEY in your environment variables. The SDK reads it automatically.

// usage

Register tools. Stream responses.

Define TickerAPI methods as AI SDK tools with typed parameters. The model calls them automatically when it needs market data.

Tool Registration lib/market-tools.ts

import { TickerAPI } from "tickerapi";
import { tool } from "ai";
import { z } from "zod";

const client = new TickerAPI(process.env.TICKERAPI_KEY);

export const marketTools = {
  getSummary: tool({
    description: "Get a market summary for a ticker",
    parameters: z.object({
      ticker: z.string().describe("Stock ticker symbol"),
    }),
    execute: async ({ ticker }) => client.getSummary(ticker),
  }),
  scanOversold: tool({
    description: "Find oversold assets",
    parameters: z.object({
      sector: z.string().optional(),
    }),
    execute: async ({ sector }) => client.scanOversold({ sector }),
  }),
};

API Route app/api/chat/route.ts

import { openai } from "@ai-sdk/openai";
import { streamText } from "ai";
import { marketTools } from "@/lib/market-tools";

export async function POST(req) {
  const { messages } = await req.json();

  const result = streamText({
    model: openai("gpt-4o"),
    messages,
    tools: marketTools,
  });

  return result.toDataStreamResponse();
}

// agent workflow

Multi-step analysis.

Your model can chain tool calls — scan for oversold stocks, then get a full summary, then compare against peers. Each call returns categorical data the model understands without extra prompting.

scanOversold(sector: "Technology")

Returns list of oversold tech tickers

getSummary(ticker: "INTC")

Full categorical breakdown for top result

compareAssets(tickers: ["INTC", "AMD"])

Side-by-side comparison

// state changes

Track state changes effortlessly.

Most market data APIs return point-in-time snapshots. TickerAPI tracks state transitions — your agent sees what changed, not just what is.

json

{
  "ticker": "AAPL",
  "changes": [
    {
      "field": "rsi_zone",
      "from": "neutral",
      "to": "oversold"
    },
    {
      "field": "trend",
      "from": "uptrend",
      "to": "downtrend"
    }
  ]
}

// what your agent sees

What your agent sees.

Every tool returns categorical facts — not raw OHLCV data. Your agent can branch on "oversold" without needing to know what RSI > 70 means.

json

{
  "ticker": "NVDA",
  "trend": "strong_uptrend",
  "momentum": {
    "rsi_zone": "overbought",
    "macd_signal": "bullish"
  },
  "volatility": "high",
  "fundamentals": {
    "pe_zone": "above_historical_avg",
    "earnings_surprise": "positive"
  }
}