Quickstart - Tako Docs

For AI agents: Use llms.txt for a full index of all documentation.

Installation

Tako ships official SDKs for Python and TypeScript / JavaScript. AI clients connect through the hosted MCP server — nothing to install, just the endpoint. Every endpoint is also a single POST, so any other language works over the REST API directly.

pip install tako-sdk

npm install tako-sdk

npm install @takoviz/ai-sdk ai @ai-sdk/openai

https://mcp.tako.com/mcp

For one-click MCP setup in Claude, ChatGPT, Cursor, and VS Code, see the MCP server page.

Get your API key

New to Tako? Sign up and get free credits to start building.

Create an API key

Create an API key from your Tako console.

Store it as an environment variable

Store it as an environment variable — for example TAKO_API_KEY — rather than hardcoding it.

Pick the right tool

Each API is a single call over the same curated, real-time data — here’s what each one is for, and why it beats a generic search API. Expand a tool to see when to reach for it.

Agent — token-efficient deep research, grounded in accurate data

Rank a cohort. “Which of the 20 largest US semiconductor companies grew revenue fastest since 2015?” — the Agent resolves the set, pulls each company’s data, and ranks them in one long-running run you dispatch and poll.
Background research job. Kick off an overnight run that compiles a competitor’s funding history, headcount, and recent filings into one cited brief, and read it when it finishes.

Learn more about Agent →

Answer — one written, cited answer in a single call

Answer in a chat assistant. A support bot hits “What was NVIDIA’s latest quarterly revenue?” mid-conversation and gets back the written answer plus its sources in one call — no retrieval to wire up.
Keep a page current. A weekly market-recap page renders “How did the S&P 500 do this week?” with the cards behind it, then re-runs each morning to keep the copy fresh.

Learn more about Answer →

Search — fast structured knowledge cards, no LLM in the loop

Mass-query for an agent. Fan out Search calls to grab fresh data fast — pull this quarter’s revenue for all 30 holdings in a portfolio at once, one call per ticker, with no LLM in the loop — then compute on the results.
Embed a live chart. A dashboard drops a live “Gold price, last 5 years” card into the page from a single query.

Learn more about Search →

Contents — the exact numbers behind an answer or search, as CSV

Feed exact numbers to an agent. After Search returns a card, the agent downloads its CSV and computes a 3-year growth rate on the real series instead of guessing from prose.
Pull a series into a notebook. An analyst pulls “US CPI, year over year” straight into a pandas dataframe or spreadsheet to chart it themselves.

Learn more about Contents →

Already have your own data? Thin-Viz turns it into interactive, embeddable Tako cards.

Make your first request

Pick the use case closest to what you’re building. Each is a single call over the same real-time data — the code and the live result below both change to match.

Stock prices
Sports
Research
Build an agent

Search returns fast, structured knowledge cards for a query — no LLM in the loop. Ideal for pulling live prices you render or compute on yourself.

Code

curl -X POST https://tako.com/api/v3/search \
  -H "X-API-Key: $TAKO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "What are today'\''s top performing stocks?"
  }'

import os
from tako import Configuration, SearchRequest
from tako.lib import Tako

config = Configuration()
config.api_key["apiKey"] = os.environ["TAKO_API_KEY"]
client = Tako(config)

results = client.search(SearchRequest(query="What are today's top performing stocks?"))
for card in results.cards or []:
    print(card.title, card.webpage_url)

import { Tako } from "tako-sdk";

const tako = new Tako({ apiKey: process.env.TAKO_API_KEY! });

const results = await tako.search({ query: "What are today's top performing stocks?" });
for (const card of results.cards ?? []) {
  console.log(card.title, card.webpage_url);
}

Result

A knowledge card — a full data series with its sources, ready to render or compute on.

Answer returns one written, source-attributed answer plus the Tako cards that back it — in a single call, no retrieval to wire up.

Code

curl -X POST https://tako.com/api/v1/answer \
  -H "X-API-Key: $TAKO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "How has Luka Dončić'\''s points per game trended this season?"
  }'

import os
from tako import Configuration, SearchRequest
from tako.lib import Tako

config = Configuration()
config.api_key["apiKey"] = os.environ["TAKO_API_KEY"]
client = Tako(config)

response = client.answer(SearchRequest(query="How has Luka Dončić's points per game trended this season?"))
print(response.answer)
for card in response.cards or []:
    print(card.title, card.webpage_url)

import { Tako } from "tako-sdk";

const tako = new Tako({ apiKey: process.env.TAKO_API_KEY! });

const response = await tako.answer({ query: "How has Luka Dončić's points per game trended this season?" });
console.log(response.answer);
for (const card of response.cards ?? []) {
  console.log(card.title, card.webpage_url);
}

Result

Answer: Luka Dončić is averaging 33.5 points per game this season. His monthly PPG has fluctuated — 38.2 in October, 32.5 in November, 31.0 in December, 34.0 in January, 27.0 in February, and back up to 37.5 in March.

Agent is an asynchronous deep-research agent for multi-step questions — resolving a cohort, then ranking it across many entities. Dispatch a run, then poll until it’s done.

Code

# 1. Dispatch — returns 202 with {"run_id": "...", "status": "queued"}.
curl -X POST https://tako.com/api/v1/agent/runs \
  -H "X-API-Key: $TAKO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "Which of the Magnificent Seven tech companies has grown revenue the fastest over the past five years?"
  }'

# 2. Poll with the run_id until status is "completed" or "failed".
curl https://tako.com/api/v1/agent/runs/RUN_ID \
  -H "X-API-Key: $TAKO_API_KEY"

import os
import time
from tako import Configuration, AgentRunRequest
from tako.lib import Tako

config = Configuration()
config.api_key["apiKey"] = os.environ["TAKO_API_KEY"]
client = Tako(config)

run = client.agent.run(
    AgentRunRequest(query="Which of the Magnificent Seven tech companies has grown revenue the fastest over the past five years?")
)

# Runs can take minutes — poll on a short interval until terminal.
while run.status not in ("completed", "failed"):
    time.sleep(3)
    run = client.agent.get(run.run_id)

print(run.result.answer)

import { Tako } from "tako-sdk";

const tako = new Tako({ apiKey: process.env.TAKO_API_KEY! });

let run = await tako.agent.run({
  query: "Which of the Magnificent Seven tech companies has grown revenue the fastest over the past five years?",
});

// Runs can take minutes — poll on a short interval until terminal.
while (run.status !== "completed" && run.status !== "failed") {
  await new Promise((r) => setTimeout(r, 3000));
  run = await tako.agent.get(run.run_id);
}

console.log(run.result?.answer);

Result

Answer: NVIDIA grew revenue the fastest over the past five years — from $16.7B in 2020 to $215.9B in 2025, a five-year CAGR of 66.9%. The rest of the Magnificent Seven trailed well behind: Tesla at 24.6%, Meta at 18.5%, Alphabet at 17.2%, Microsoft at 14.5%, Amazon at 13.2%, and Apple at 8.7%.

Prime an agent with exact, source-grounded numbers: Search finds the card, then Contents downloads the exact series behind it as CSV — so your agent computes on real values instead of prose.

Code

# 1. Search finds the card.
curl -X POST https://tako.com/api/v3/search \
  -H "X-API-Key: $TAKO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "Palantir federal contract obligations"}'

# 2. Contents downloads the exact numbers behind it (pass the card's webpage_url).
curl -X POST https://tako.com/api/v1/contents \
  -H "X-API-Key: $TAKO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://tako.com/card/IbVGstkzEIUt8nwY4G_1/",
    "mode": "inline"
  }'

import os
from tako import Configuration, SearchRequest
from tako.models.contents_request import ContentsRequest
from tako.lib import Tako

config = Configuration()
config.api_key["apiKey"] = os.environ["TAKO_API_KEY"]
client = Tako(config)

# 1. Search finds the card.
results = client.search(SearchRequest(query="Palantir federal contract obligations"))
card = results.cards[0]

# 2. Contents downloads the exact numbers behind it — feed the CSV to your agent.
contents = client.contents(ContentsRequest(url=card.webpage_url, mode="inline"))
print(contents.contents[0].data)

import { Tako } from "tako-sdk";

const tako = new Tako({ apiKey: process.env.TAKO_API_KEY! });

// 1. Search finds the card.
const results = await tako.search({ query: "Palantir federal contract obligations" });
const card = results.cards![0];

// 2. Contents downloads the exact numbers behind it — feed the CSV to your agent.
const contents = await tako.contents({ url: card.webpage_url, mode: "inline" });
console.log(contents.contents[0].data);

Result

Search finds the card — Palantir’s federal contract obligations by fiscal year:

Contents hands your agent the exact series behind it, as CSV — ready to compute on:

Timestamp,usaspending_sum_obligation - Palantir Technologies Inc. Federal Contract Obligations
2008-10-01 00:00:00+00:00,135211.06
2009-10-01 00:00:00+00:00,4378216.96
2010-10-01 00:00:00+00:00,5801023.5
...
2024-10-01 00:00:00+00:00,541197885.14
2025-10-01 00:00:00+00:00,1020566208.97
2026-10-01 00:00:00+00:00,713329284.7

Next steps

Developer Playground

No setup required. Try a simple query like “Nvidia earnings” or a long-form prompt to see what Tako returns.

What is Tako?

Learn more about Tako’s key concepts and functionality.

​Installation

​Get your API key

​Pick the right tool

​Make your first request

​Next steps

Developer Playground

What is Tako?

Installation

Get your API key

Pick the right tool

Make your first request

Next steps