How to give your AI agent company financial data

Ask Tako's Search API for a company's numbers in plain language, like “Apple vs Microsoft quarterly revenue” or “Nvidia gross margin”. It returns financial statements, analyst estimates, ratios and stock prices from S&P Global, Fiscal.ai, Visible Alpha and QUODD, with the source on every result, plus a chart you can embed. Or connect Tako's MCP server and ask Claude, Cursor or ChatGPT directly.

COVERAGE

What company data Tako covers

Financial statements
Income statement, balance sheet and cash flow, quarterly and annual, including segments. From S&P Global and Fiscal.ai.
Analyst estimates
Estimates against actuals for EPS, revenue, EBITDA, free cash flow, margins and more, with earnings surprises. From S&P Global.
Ratios and valuation
P/E, margin, liquidity, solvency and dividend ratios, plus EV/Revenue, EV/EBITDA and market cap, reported and forward. From S&P Global and Fiscal.ai.
Stock prices
Prices and volume by the minute, the half hour and the day, with up to 35 years of daily history for listed stocks and ETFs. From QUODD.
Segments and KPIs
Operating metrics reported by business segment. From Visible Alpha.
Private companies and deals
Funding rounds, post-money valuations, and M&A deals with value, status and advisors. From S&P Global.
Freshness
Financial statements, ratios and segment KPIs refresh daily, analyst estimates hourly, and stock prices through the trading day.

QUICKSTART

Get company financials with one API call

Send the question as the query to the Search API, with your API key in the X-API-Key header. Name the company and the figure, the way an analyst would ask. Tako returns the matching series with its source, so your agent quotes reported numbers instead of guessing them. Every parameter is in the Search API docs.

Python
import os
import requests

response = requests.post(
    "https://tako.com/api/v3/search",
    headers={"X-API-Key": os.environ["TAKO_API_KEY"]},
    json={"query": "Apple vs Microsoft quarterly revenue"},
    timeout=30,
)
for card in response.json()["outputs"]["knowledge_cards"]:
    print(card["title"], card["sources"][0]["source_name"], card["webpage_url"])

RESPONSE

What the call returns

A Search API call returns knowledge cards and web results as JSON. Below is a real response, trimmed to the top card and the first web results.

Each result comes back as JSON from the Search API and as an interactive card you can embed in your app. Where the source allows it, the Contents API returns the card's rows as CSV; some licensed data, such as S&P Global's, can be shown in a card but not exported. Every result names its source.

Query

“Apple vs Microsoft quarterly revenue”

JSON response

A real response, captured September 30, 2026.

{
  "outputs": {
    "knowledge_cards": [
      {
        "card_id": "PLymjx46ZJG3cNE4Iq2E",
        "title": "Microsoft Corporation, Apple Inc - Total Revenues (Normalized) (Quarterly)",
        "description": "Microsoft Corporation Total Revenues (Normalized) (Quarterly)'s latest value was $90,007,000,000 for fiscal Q4 2026, the quarter ending Jun 2026, … Apple Inc. Total Revenues (Normalized) (Quarterly)'s latest value was $109,417,000,000 for fiscal Q3 2026, …",
        "webpage_url": "https://tako.com/card/PLymjx46ZJG3cNE4Iq2E/",
        "embed_url": "https://tako.com/embed/PLymjx46ZJG3cNE4Iq2E/",
        "sources": [
          {
            "source_name": "Fiscal.ai",
            "source_index": "data"
          }
        ],
        "card_type": "chart",
        "relevance": "High",
        "exportable": true,
        "metric_definitions": [
          {
            "name": "Total Revenues (Normalized)",
            "definition": "Total income earned from a company's core business activities, including the sale of goods or the rendering of services. …"
          }
        ],
        "data_freshness": {
          "coverage_end": "2026-06",
          "data_as_of": "2026-09-30",
          "last_updated": "2026-09-30"
        }
      }
    ],
    "web_results": [
      {
        "title": "Apple vs Microsoft (AAPL vs MSFT) Compared | Analyze Portfolio",
        "url": "https://analyzeportfolio.com/stocks/compare/AAPL-vs-MSFT",
        "source_name": "analyzeportfolio.com"
      },
      {
        "title": "Apple Inc. (AAPL) vs Microsoft (MSFT) — Revenue, Margins, FCF & Balance Sheet | 10q10k.net",
        "url": "https://10q10k.net/compare/AAPL-vs-MSFT",
        "source_name": "10q10k.net"
      },
      {
        "title": "Microsoft Revenue 2012-2026 | MSFT | MacroTrends",
        "url": "https://www.macrotrends.net/stocks/charts/MSFT/microsoft/revenue",
        "source_name": "macrotrends.net"
      }
    ]
  },
  "request_id": "3f6cc910-cb6c-4475-ae24-462bba93f413"
}

Card

Want a one-line answer instead, like whether Apple beat estimates, with its sources? See how to add citations to your AI chatbot.

CLAUDE, CURSOR, CHATGPT

A financial data MCP server for Claude, Cursor and ChatGPT

Tako's MCP server gives any MCP client the same data. No API key is needed: you sign in with a Tako account the first time you use it. Then ask in plain language, for example “How has Microsoft's operating margin changed over the last eight quarters?”.

  1. Claude Code

    Run claude mcp add --transport http tako https://mcp.tako.com/mcp, then /mcp to sign in.

  2. Claude.ai

    Open Settings, then Connectors, then Add custom connector, and paste https://mcp.tako.com/mcp.

  3. Cursor

    Add a server named tako with the URL https://mcp.tako.com/mcp to .cursor/mcp.json.

  4. ChatGPT

    In developer mode, add a plugin with the connector URL https://mcp.tako.com/mcp/chatgpt.

Every other client, from VS Code to Gemini CLI, is on the Tako MCP page.

FAQ

Frequently asked questions

Where does Tako's financial data come from?

From licensed providers: S&P Global and Fiscal.ai for financial statements, estimates and ratios, Visible Alpha for segment metrics, and QUODD for stock prices. Every result names its source.

Can my agent calculate ratios or growth?

Often it doesn't need to: Tako returns common ratios, margins and valuation multiples already calculated. For anything else, ask the Answer API for a written answer built on the same data, or download a card's rows with the Contents API where the source allows export.

How is this different from reading filings with an LLM?

A model reading a filing has to find and extract each number, and can misread one. Tako returns the figure itself as structured data with its source, so your agent starts from the number instead of the document.

How current is the data, and how far back does it go?

Financial statements, ratios and segment KPIs refresh daily, analyst estimates hourly, and stock prices through the trading day. Daily price history goes back up to 35 years for listed stocks and ETFs. Every card shows when its data was last updated.

Can I show S&P Global data in my app?

Yes, as a card: embed it and your users see the chart with S&P Global named as the source. S&P Global's rows can't be exported as CSV through the Contents API; Fiscal.ai's can.

Start building with Tako

Mistral's Le Chat and Liner embed Tako knowledge cards in their answers. Your first 2,000 requests are free.