Nasdaq Data Link connector for AI agents

CALL ANY TOOL

6 tools for financial data on Nasdaq Data Link: search time-series datasets, read database and dataset metadata, get observations, and query data tables.

nasdaqdatalink_get_database

Get database

Get the metadata of a Nasdaq Data Link time-series database by its code. Returns database.id, name, database_code, description, datasets_count, downloads, premium and url_name. Use nasdaqdatalink_get_database to see what a database such as FRED holds and whether it is premium. Use nasdaqdatalink_search_datasets with database_code to list its datasets.

Parameters

Name

Type

Required

Description

database_code

string

Required

Time-series database code, such as FRED. It is the part before the slash in a dataset code like FRED/GDP.

nasdaqdatalink_get_table_metadata

Get table metadata

nasdaqdatalink_get_time_series_data

Get time series data

Get the observations of a Nasdaq Data Link time-series dataset (Time-series API), with optional date range, row limit, single-column selection, frequency collapse and transformation. Returns dataset_data.column_names (the first is the date), dataset_data.data (one array per date), plus frequency, start_date, end_date and the options applied. Premium databases need a subscription. Use nasdaqdatalink_get_time_series_data for a dataset code such as FRED/GDP. Use nasdaqdatalink_query_table for a data table such as ZACKS/FC. Use nasdaqdatalink_search_datasets to find a dataset code.

Parameters

Name

Type

Required

Description

database_code

string

Required

Time-series database code: the part before the slash in a dataset code such as FRED/GDP. Uppercase letters, digits and underscores. Example: FRED.

dataset_code

string

Required

Dataset code within the database: the part after the slash in a dataset code such as FRED/GDP. Example: GDP.

collapse

string

Optional

Lower the data frequency. Each period keeps its last observation, so sums or averages are not computed. Values: none, daily, weekly, monthly, quarterly, annual. Only downsampling works; a frequency higher than the dataset's is not created. One of: `none`, `daily`, `weekly`, `monthly`, `quarterly`, `annual`.

column_index

integer

Optional

Return only one data column, by position. Column 0 is the date and is always returned; data columns start at 1. Example: 4 returns the date and the fourth data column.

end_date

string

Optional

Latest date to return, inclusive, as yyyy-mm-dd. Example: 2020-12-31.

limit

integer

Optional

Return only the first n rows after ordering. With the default newest-first order, limit 1 returns the latest observation. Example: 10.

order

string

Optional

Row order by date: desc (newest first, the API default) or asc (oldest first). One of: `asc`, `desc`.

start_date

string

Optional

Earliest date to return, inclusive, as yyyy-mm-dd. Example: 2015-01-01.

transform

string

Optional

Calculation applied before the data is returned: none, diff (change from the previous row), rdiff (percentage change from the previous row, as a fraction), rdiff_from (change from each row to the latest value, as a fraction), cumul (cumulative sum) or normalize (rebased so the first row is 100). One of: `none`, `diff`, `rdiff`, `rdiff_from`, `cumul`, `normalize`.

nasdaqdatalink_get_time_series_metadata

Get time series metadata

nasdaqdatalink_query_table

Query table

nasdaqdatalink_search_datasets

Search datasets

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Nasdaq Data Link tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["nasdaqdatalink"], toolNames: [
    "nasdaqdatalink_search_datasets",
    "nasdaqdatalink_get_time_series_metadata",
    "nasdaqdatalink_get_time_series_data"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find the US unemployment rate dataset and show the last 24 months" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["nasdaqdatalink"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find the US unemployment rate dataset and show the last 24 months" }],
  tools,
});

// Execute the tool call with the user's vaulted Nasdaq Data Link API key
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["nasdaqdatalink"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find the US unemployment rate dataset and show the last 24 months" }],
  tools,
});

// Tool call runs with the user's vaulted Nasdaq Data Link API key
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["nasdaqdatalink"] }, pageSize: 100,
});

const agent = new Agent({
  name: "data_research_agent",
  model: "gemini-2.5-pro",
  instruction: "Nasdaq Data Link tools scoped to this user",
  tools,
});

await agent.run("Find the US unemployment rate dataset and show the last 24 months");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Nasdaq Data Link tool. Click to copy, paste into your agent, done.

Discovery

Copy the prompt

Copied

Search for datasets about US housing starts.

Copy the prompt

Copied

What does the FRED database hold, and is it premium?

Copy the prompt

Copied

What columns and date range does FRED/GDP cover?

Time series

Copy the prompt

Copied

Show quarterly FRED/GDP for the last 5 years.

Copy the prompt

Copied

Get FRED/UNRATE as a percent change since 2020.

Copy the prompt

Copied

Collapse FRED/DFF to monthly values for 2024.

Data tables

Copy the prompt

Copied

Which columns can I filter on in the ZACKS/FC table?

Copy the prompt

Copied

Query ZACKS/FC rows for ticker AAPL.

Copy the prompt

Copied

Fetch the next page of results for that query.

SEE HOW AUTH WORKS

Each user connects their own Nasdaq Data Link API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.

1

Authorize

Your user connects

Nasdaq Data Link

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Nasdaq Data Link

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Nasdaq Data Link

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Nasdaq Data Link

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other finance and market data connectors.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

GTM and RevOps Teams

Revenue forecast commentary

Pulls open pipeline from Salesforce and HubSpot, calculates coverage against quota, flags at-risk stages, posts commentary to Slack, and logs every snapshot to Google Sheets.

Test other agents

See the same per-user auth pattern across other finance and market data connectors.

GTM

Competitive intelligence briefing agent

Scan Gong calls for competitor mentions, match each one to its Notion battlecard, and DM every affected rep a single Slack digest.

GTM

Revenue forecast agent

Score pipeline coverage against quota across Salesforce and HubSpot, post forecast commentary to Slack, log snapshots to Sheets.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Nasdaq Data Link API key looks fine in a demo. In production every dataset query looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Nasdaq Data Link today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Nasdaq Data Link as the user or through a shared API key?

As the user. Each user connects their own Nasdaq Data Link API key once, and Scalekit sends it with every call. Audit logs attribute every dataset query to that user, not a shared service account.

Where is the Nasdaq Data Link API key stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Nasdaq Data Link?

Yes. All 6 Nasdaq Data Link tools are read-only: they search, describe, and read datasets and tables and never change anything. You can still filter by tool name in listScopedTools to expose a smaller set, for example only nasdaqdatalink_search_datasets and nasdaqdatalink_get_time_series_data. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Nasdaq Data Link access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent read premium Nasdaq Data Link data?

Only data the user's subscription covers. Premium databases and premium tables need a subscription, while free tables work with any key. nasdaqdatalink_get_database and nasdaqdatalink_search_datasets show whether a database or dataset is premium.

Nasdaq Data Link MCP server for AI agents

Tools your data research agent reaches for on Nasdaq Data Link, scoped per user.